WO2017130486A1 - 情報処理装置、情報処理方法およびプログラム - Google Patents
情報処理装置、情報処理方法およびプログラム Download PDFInfo
- Publication number
- WO2017130486A1 WO2017130486A1 PCT/JP2016/081470 JP2016081470W WO2017130486A1 WO 2017130486 A1 WO2017130486 A1 WO 2017130486A1 JP 2016081470 W JP2016081470 W JP 2016081470W WO 2017130486 A1 WO2017130486 A1 WO 2017130486A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- user
- text
- voice
- control unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
- G10L13/033—Voice editing, e.g. manipulating the voice of the synthesiser
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/221—Announcement of recognition results
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Definitions
- This disclosure relates to an information processing apparatus, an information processing method, and a program.
- the voice recognition process result obtained by the voice recognition process is output by the voice output device in a predetermined voice output mode.
- the information acquisition unit that acquires information related to the accuracy of the speech recognition processing for the sound information based on the collected sound, and the sound output mode of the speech recognition processing result is controlled based on the information related to the accuracy of the speech recognition processing.
- An information processing apparatus is provided.
- the information regarding the accuracy of the speech recognition processing for the sound information based on the sound collection is acquired, and the speech output mode of the speech recognition processing result is obtained by the processor based on the information regarding the accuracy of the speech recognition processing. And an information processing method is provided.
- the computer obtains information regarding the accuracy of the speech recognition processing for the sound information based on the sound collection, and outputs the speech recognition processing result based on the information regarding the accuracy of the speech recognition processing.
- a program for causing an information processing apparatus to include an output control unit for controlling an aspect for controlling an aspect.
- a plurality of constituent elements having substantially the same functional configuration may be distinguished by adding different numerals after the same reference numerals. However, when it is not necessary to particularly distinguish each of a plurality of constituent elements having substantially the same functional configuration, only the same reference numerals are given.
- FIG. 2 is a diagram illustrating a configuration example of a communication system according to an embodiment of the present disclosure.
- the communication system according to the present embodiment includes an information processing system 10-1 and an information processing system 10-2.
- Each of the information processing system 10-1 and the information processing system 10-2 includes an image input unit 110, an operation input unit 115, a biological information input unit 118, a sound collection unit 120, a display unit 130, a sound output unit 150, and an information processing apparatus ( Hereinafter, it is also referred to as “control unit”) 140.
- the information processing apparatus 140 in the information processing system 10-1 and the information processing apparatus 140 in the information processing system 10-2 can communicate via the communication network 931.
- the image input unit 110, the sound collection unit 120, and the sound output unit 150 are provided in the frame of the display unit 130, but the image input unit 110, the sound collection unit 120, and the sound output unit 150 are included.
- the position where is provided is not limited.
- the image input unit 110, the sound collection unit 120, and the sound output unit 150 may be provided at a position other than the frame on the display unit 130, or at a position different from the display unit 130 (for example, the operation input unit 115).
- Sound information provided and collected by the sound collection unit 120 may be transmitted to the information processing apparatus 140.
- the sound collection unit 120 and the sound output unit 150 may be provided in a device (for example, a headset) independent of the display unit 130 or the like.
- the information processing apparatus 140 is a game machine, but the form of the information processing apparatus 140 is not limited to a game machine.
- the information processing apparatus 140 may be a smartphone, a mobile phone, a tablet terminal, or a PC (Personal Computer).
- the display unit 130 is a television device, but the display unit 130 is not limited to the television device. In the following description, a voice (voice or speech) and a sound are used separately.
- FIG. 1 is a block diagram illustrating a functional configuration example of an information processing system 10 according to the present embodiment.
- the information processing system 10 includes an image input unit 110, an operation input unit 115, a biological information input unit 118, a sound collection unit 120, a communication unit 125, a display unit 130, and a sound.
- An output unit 150 and a control unit 140 are provided.
- the image input unit 110 has a function of inputting an image.
- the image input unit 110 includes a camera, and inputs an image captured by the camera.
- the number of cameras included in the image input unit 110 is not particularly limited as long as it is one or more. Further, the position where each of the one or more cameras included in the image input unit 110 is provided is not particularly limited.
- the one or more cameras may include a monocular camera or a stereo camera.
- the operation input unit 115 has a function of inputting a user operation.
- the operation input unit 115 may include a game machine controller.
- the operation input unit 115 may include a touch panel as long as it has a function of inputting a user operation.
- the method employed by the touch panel is not particularly limited, and may be a capacitance method, a resistance film method, an infrared method, or an ultrasonic method.
- the operation input unit 115 may include a camera.
- the biometric information input unit 118 has a function of inputting biometric information of the user.
- the biometric information input unit 118 includes a pressure sensor, it is possible to input the grasping pressure of the controller by the user as biometric information using the pressure sensor.
- the biometric information input unit 118 includes a heartbeat sensor, the heartbeat sensor can input the user's heartbeat as biometric information.
- the biological information input unit 118 includes a sweat sensor, it is possible to input the user's sweat as biological information using the sweat sensor.
- the biometric information input unit 118 may be provided in the wearable device.
- the sound collection unit 120 has a function of obtaining sound information by collecting sound. As described with reference to FIG. 2, the sound collection unit 120 may be provided in the frame of the display unit 130, but may be provided in a position other than the frame in the display unit 130, or the display unit 130. It may be provided at a different position (for example, the operation input unit 115).
- the number of microphones included in the sound collection unit 120 is not particularly limited as long as it is one or more. Also, the position where each of the one or more microphones included in the sound collection unit 120 is provided is not particularly limited.
- the arrival direction of the sound can be estimated based on sound information obtained by sound collection by each of the plurality of microphones.
- the sound collection part 120 contains the microphone which has directivity, the arrival direction of a sound can be estimated based on the sound information obtained by the sound collection by the microphone which has directivity.
- the control unit 140 executes control of each unit of the information processing system 10. As illustrated in FIG. 1, the control unit 140 includes an information acquisition unit 141, a voice recognition unit 142, an output control unit 143, and an output unit 144. Details of these functional blocks will be described later.
- the control unit 140 may be configured by, for example, a CPU (Central Processing Unit).
- the processing device may be configured by an electronic circuit.
- the communication unit 125 has a function of performing communication with another information processing system 10.
- the communication unit 125 is configured by a communication interface.
- the communication unit 125 can communicate with another information processing system 10 via the communication network 931 (FIG. 2).
- the display unit 130 has a function of displaying a screen.
- the display unit 130 may be a liquid crystal display, an organic EL (Electro-Luminescence) display, or an HMD (Head Mount Display).
- the display unit 130 may be a display of another form as long as it has a function of displaying a screen.
- the sound output unit 150 has a function of outputting sound information.
- the sound output unit 150 may be a speaker, a headphone, or an earphone.
- the sound output unit 150 may be another form of sound output device as long as it has a function of outputting sound information.
- FIG. 3 is a diagram for explaining an overview of the information processing system 10.
- the display unit 130 includes a video display screen 131 on which a video reproduced by the control unit 140 is displayed.
- the video displayed on the video display screen 131 is a video included in the game application.
- a chat application for allowing the user U1 of the information processing system 10-1 to chat with the user of the information processing system 10-2 is executed by the control unit 140, and the display unit 130
- the execution screen is displayed as a chat screen 134.
- the voice recognition processing result for the sound information including the utterance of the user U1 and the voice recognition processing result for the sound information including the utterance of the user of the information processing system 10-2 are displayed on the chat screen 134.
- the speech recognition processing result may be single character data obtained by performing speech recognition processing on sound information or character string data in which a plurality of characters are arranged.
- the voice recognition processing result may be a reading result by the system of one character data or character string data obtained in this way.
- “text” and “text reading result” are used as examples of the speech recognition processing result.
- a recognition result screen 133 on which text is displayed also exists on the display unit 130.
- the recognition result screen 133 is included in the utterance screen 135, and the utterance screen 135 has a voice recognition process start button 132 for starting the voice recognition process.
- the voice recognition process start button 132 is a GUI (Graphical User Interface) button
- the voice recognition process start button 132 is included in a hardware button (for example, the operation input unit 115). Hardware button).
- the recognition start operation is input by the operation input unit 115, and the information acquisition unit 141 collects the information.
- the sound information collected by the sound unit 120 is acquired, and the speech recognition unit 142 starts speech recognition processing for the sound information. At this time, the user U1 starts speaking.
- the signal collected by the sound collection unit 120 is referred to as sound information, but the sound information is obtained by performing some signal processing on the signal collected by the sound collection unit 120. It may be a received signal. Then, when the text recognition process is executed by the voice recognition unit 142 and the text Tx-10 is obtained, the output unit 144 outputs the text Tx-10 to the display unit 130.
- the display unit 130 displays the text Tx-10 output by the output unit 144 on the recognition result screen 133.
- the user U1 utters “Let's play game.”,
- the recognition result screen 133 shows the sound collected by the sound collection unit 120 of the information processing system 10-1.
- the text Tx-10 “Et's play game.” Is displayed.
- the output control unit 143 reads out the text Tx-10 “Et's play game.”
- the sound output unit 150 outputs the read-out result of the text Tx-10.
- the recognition result screen 133 displays a voice recognition process end button 136 for ending the voice recognition process.
- the recognition end operation is input by the operation input unit 115, and the voice recognition unit 142
- the output control unit 143 causes the text Tx-10 to be added to the chat screen 134.
- the text Tx-10 is transmitted to the control unit 140 in the information processing system 10-2 and displayed on the chat screen in the information processing system 10-2.
- the information acquisition unit 141 acquires information related to the accuracy of the speech recognition process for the sound information. Further, the output control unit 143 reads out the text Tx-10, and controls the voice output mode of the read-out result of the text Tx-10 based on information on the accuracy of the voice recognition process. Then, the output unit 144 outputs a reading result according to the controlled voice output mode to the sound output unit 150. The sound output unit 150 outputs the reading result output from the output unit 144.
- the voice output mode of the reading result of the text Tx-10 is controlled based on the information related to the accuracy of the voice recognition process. According to such a configuration, it is possible to make the user U1 know the accuracy of the speech recognition processing by the speech output mode of the reading result of the text Tx-10.
- control of the voice output mode is performed for each sentence
- the control unit of the voice output mode is not particularly limited.
- the voice output mode may be controlled for each word or for each phrase.
- the information regarding the accuracy of the voice recognition processing is not particularly limited.
- the information related to the accuracy of the voice recognition process may include information related to the speech of the user U1 included in the sound information collected by the sound collection unit 120.
- the information related to the utterance of the user U1 is at least one of the utterance volume of the user U1, the clarity of the utterance of the user U1, and the utterance length of the user U1 included in the sound information collected by the sound collection unit 120. One may be included.
- the information related to the accuracy of the voice recognition process may include information related to noise corresponding to the utterance of the user U1 included in the sound information collected by the sound collection unit 120.
- the information regarding noise may include the volume of noise included in the sound information collected by the sound collection unit 120.
- the voice output mode of the reading result of the text Tx-10 is not particularly limited.
- the voice output mode of the reading result of the text Tx-10 may include the voice output speed by the sound output unit 150 of the reading result of the text Tx-10.
- a specific example will be described.
- FIG. 4 is a diagram showing an example of the audio output speed according to the noise volume and the utterance volume.
- the accuracy of the voice recognition processing is lower when the noise volume is smaller than the noise volume determination threshold, compared to the case where the noise volume is smaller than the noise volume determination threshold. Therefore, in such a case, the output control unit 143 may make it easier for the user U1 to grasp the reading result of the text Tx-10 by reducing the voice output speed.
- the output control unit 143 may finish reading the text Tx-10 earlier by increasing the voice output speed.
- the output control unit 143 may make it easier for the user U1 to grasp the reading result of the text Tx-10 by reducing the voice output speed.
- the output control unit 143 may finish reading the text Tx-10 earlier by increasing the voice output speed.
- the noise volume is smaller than the threshold for determining the noise volume.
- the output control unit 143 may make it easier for the user U1 to grasp the reading result of the text Tx-10 by reducing the voice output speed.
- FIG. 5 is a diagram showing an example of the voice output speed according to the utterance length and the utterance volume.
- the output control unit 143 may make it easier for the user U1 to grasp the reading result of the text Tx-10 by reducing the voice output speed.
- the output control unit 143 may finish reading the text Tx-10 earlier by increasing the voice output speed.
- the utterance length is a threshold for determining the utterance length in a predetermined section (in the example shown in FIG. 5, the section in which the utterance volume is larger than the threshold for determining the utterance volume). It is considered that the accuracy of the speech recognition process is reduced when the utterance length is shorter than the utterance length determination threshold as compared to the longer case. Therefore, in such a case, the output control unit 143 may make it easier for the user U1 to grasp the reading result of the text Tx-10 by reducing the voice output speed.
- the clarification of the utterance may be handled in the same manner as the utterance volume and the utterance length. That is, it is considered that the accuracy of the speech recognition processing is reduced when the utterance clarity is smaller than the utterance clarity determination threshold value, compared to when the utterance clarity is greater than the utterance clarity determination threshold value. . Therefore, in such a case, the output control unit 143 may make it easier for the user U1 to grasp the reading result of the text Tx-10 by reducing the voice output speed. On the other hand, when the utterance clarity is greater than the utterance clarity determination threshold, the output control unit 143 may finish reading the text Tx-10 earlier by increasing the voice output speed. .
- the information related to the accuracy of the voice recognition process may include the reliability of the voice recognition process result.
- the reliability is acquired from the voice recognition unit 142.
- FIG. 6 is a diagram illustrating an example of the audio output speed according to the reliability and the speech volume. As shown in FIG. 6, it is considered that the accuracy of the speech recognition process is reduced when the reliability is lower than the reliability determination threshold as compared to when the reliability is higher than the reliability determination threshold. Therefore, in such a case, the output control unit 143 may make it easier for the user U1 to grasp the reading result of the text Tx-10 by reducing the voice output speed. On the other hand, when the reliability is greater than the threshold for determining reliability, the output control unit 143 may finish reading the text Tx-10 earlier by increasing the voice output speed.
- the voice output speed is indicated by how many times the reading speed is based on the normal reading speed of the normal text Tx-10 by the output control unit 143.
- the reference reading speed is not limited to this.
- the reference reading speed may be a reading speed in consideration of the speech speed of the user U1.
- the reference reading speed may be a reading speed in consideration of the frequency with which the user U1 exchanges with other users through chat.
- the voice output speed is used as an example of the voice output mode, but the voice output mode is not limited to this example.
- the voice output mode may include the type of output voice (hereinafter also referred to as “Prefix”) that is output before the voice output of the text Tx-10 is read out. That is, the output control unit 143 may control the type of Prefix based on information related to the accuracy of the audio processing result.
- the type of Prefix is not particularly limited, and is a word (for example, check, confirmation required, warning, etc.) or sound (for example, the type of sound effect, the number of times the sound effect is emitted) that is issued to attract the user U1's attention It may be.
- FIG. 7 is a diagram showing an example of the presence or absence of Prefix according to the noise volume and the speech volume.
- the output control unit 143 may add Prefix to the reading result of the text Tx-10 so that the user U1 can easily understand the reading result of the text Tx-10.
- the output control unit 143 reads out the text Tx-10 earlier by not attaching Prefix to the reading result of the text Tx-10. It is good to end.
- the output control unit 143 may add Prefix to the reading result of the text Tx-10 so that the user U1 can easily understand the reading result of the text Tx-10.
- the output control unit 143 reads out the text Tx-10 earlier by not attaching Prefix to the reading result of the text Tx-10. It is good to end.
- the noise volume is smaller than the threshold for determining the noise volume.
- the output control unit 143 may make it easier for the user U1 to grasp the reading result of the text Tx-10 by reducing the voice output speed.
- FIG. 8 is a diagram showing an example of the presence or absence of Prefix according to the utterance length and the utterance volume.
- the output control unit 143 may add Prefix to the reading result of the text Tx-10 so that the user U1 can easily understand the reading result of the text Tx-10.
- the output control unit 143 reads out the text Tx-10 by not adding Prefix to the reading result of the text Tx-10. It is better to finish earlier.
- the utterance length is a threshold for determining the utterance length. It is considered that the accuracy of the speech recognition process is reduced when the utterance length is shorter than the utterance length determination threshold as compared to the longer case.
- the output control unit 143 may add Prefix to the reading result of the text Tx-10 so that the user U1 can easily understand the reading result of the text Tx-10.
- the clarification of the utterance may be handled in the same manner as the utterance volume and the utterance length. That is, as described above, when the utterance clarity is smaller than the utterance clarity determination threshold value compared to when the utterance clarity is greater than the utterance clarity determination threshold value, the accuracy of the speech recognition processing is improved. Is expected to decrease. In such a case, the output control unit 143 may add Prefix to the reading result of the text Tx-10 so that the user U1 can easily understand the reading result of the text Tx-10.
- the output control unit 143 reads out the text Tx-10 by not adding Prefix to the reading result of the text Tx-10. It is better to finish the process sooner.
- the information related to the accuracy of the voice recognition process may include the reliability of the voice recognition process result.
- FIG. 9 is a diagram illustrating an example of an audio output speed according to the reliability and the speech volume. As shown in FIG. 9, it is considered that the accuracy of the speech recognition process is reduced when the reliability is lower than the reliability determination threshold as compared with the case where the reliability is higher than the reliability determination threshold. In such a case, the output control unit 143 may add Prefix to the reading result of the text Tx-10 so that the user U1 can easily understand the reading result of the text Tx-10. On the other hand, when the reliability is greater than the threshold value for determining the reliability, the output control unit 143 reads out the text Tx-10 earlier by not attaching Prefix to the reading-out result of the text Tx-10. It is good to end.
- the information regarding the accuracy of the speech recognition process may include the amount of the text Tx-10.
- FIG. 10 is a diagram illustrating an example of the relationship between the amount of text Tx-10 and the voice output speed. For example, when the amount of the text Tx-10 is larger than the predetermined text amount threshold than when the amount of the text Tx-10 is smaller than the predetermined text amount threshold, it takes a lot of time to read out. It is assumed that it becomes difficult for the user U1 to determine whether or not the text Tx-10 is normal. In such a case, as shown in FIG. 10, the output control unit 143 may shorten the time required for reading by increasing the voice output speed as the amount of the text Tx-10 increases.
- the voice output speed is indicated by how many times the reading speed of the normal text Tx-10 by the output control unit 143 is used as a reference.
- the reference reading speed is not limited to this.
- the reference reading speed may be a reading speed in consideration of the speech speed of the user U1.
- the reference reading speed may be a reading speed in consideration of the frequency with which the user U1 exchanged by chat.
- it is not limited how many times the voice output speed is set as a reference reading speed.
- the output control unit 143 may control the voice output mode based on the frequency (frequency of executing voice recognition processing) that the user U1 exchanges with other users through chat.
- the output control unit 143 may control the voice output speed of the reading result of the text Tx-10 based on the frequency of the user U1 interacting with other users by chat (frequency of executing the voice recognition process). .
- the output control unit 143 may decrease the voice output speed of the read-out result of the text Tx-10 as the frequency at which the user U1 interacts with other users through chat (the frequency of execution of the voice recognition process) increases. .
- the output control unit 143 may control the type of Prefix according to the frequency (the execution frequency of the voice recognition process) that the user U1 exchanges with other users through chat. For example, the output control unit 143 reads out the text Tx-10 when the frequency at which the user U1 interacts with other users through chat (the frequency at which the speech recognition process is performed) is smaller than the threshold for determining the execution frequency. May be prefixed with Prefix. On the other hand, the output control unit 143 reads out the text Tx-10 when the frequency at which the user U1 interacts with other users through chat (the frequency of execution of the speech recognition process) is greater than the threshold for determining the execution frequency. It is not necessary to attach Prefix to.
- the output control unit 143 may control the audio output mode based on the type of content using the text Tx-10.
- the reading result of the text Tx-10 needs to be stronger than when the content using the text Tx-10 is a chat application.
- the output control unit 143 The voice output speed of the result of reading out Tx-10 may be made smaller.
- the output control unit 143 may control the audio output mode based on information regarding the user U1.
- the information regarding the user U1 is not particularly limited, but the behavior information of the user U1, the posture information of the user U1, the setting information by the user U1, the environment information around the user U1, the biological information of the user U1, and the emotion information of the user U1 May include at least one of them.
- the biometric information of the user U1 and the emotion information of the user U1 are used directly, but the biometric information of the user U1 and the emotion information of the user U1 are once converted into the concentration level of the user U1, and the concentration level of the user U1 May be used as
- the action information of the user U1 is not particularly limited.
- the action information of the user U1 is the action recognition result of the user U1 obtained by analyzing the position information of the user U1 (for example, in a stationary state, walking State, running state, stair climbing state, and car driving state), or the moving speed of the user U1 obtained by analysis of the position information of the user U1.
- the output control unit 143 assumes that the speech is normally performed and the accuracy of the speech recognition processing is increased when the user U1 is stationary and walking, and therefore the text Tx. It is not necessary to output the reading result of -10. On the other hand, when the user U1 is running, the output control unit 143 outputs a result of reading the text Tx-10 because it is expected that the speech is not normally performed and the accuracy of the speech recognition process is lowered. May be.
- the posture information of the user U1 is acquired based on the acceleration detected by the acceleration sensor.
- the output control unit 143 may output the reading result of the text Tx-10 when the posture of the user U1 is tilted more than the tilt for posture determination.
- the output control unit 143 does not need to output the reading result of the text Tx-10 when the posture of the user U1 is not tilted more than the tilt for posture determination.
- the setting information of the user U1 is set based on the voice output mode change operation when a predetermined voice output mode change operation is selected by the user U1 and the voice output mode change operation is input by the operation input unit 115.
- the voice output mode change operation is not particularly limited, and may be an operation of selecting a voice output mode change button (not shown), for example.
- the environmental information around the user U1 may be obtained by analysis of an image input by the image input unit 110, or may be obtained by analysis of sound information collected by the sound collection unit 120.
- the environment information around the user U1 may be information indicating whether or not there is a person around the user U1.
- the output control unit 143 determines that the user wants to finish reading the text Tx-10 earlier when there is a person around the user U1 than when there is no person around the user U1. Since there is a possibility that U1 may consider, it is better to increase the voice output speed.
- the environmental information around the user U1 may be the illuminance around the user U1.
- the output control unit 143 may have difficulty in visually recognizing the text Tx-10. The result should be output.
- the output control unit 143 may be able to visually recognize the text Tx-10 when the illuminance around the user U1 is higher than the threshold for illuminance determination. Need not be output.
- the biometric information of the user U1 may be obtained in any way.
- the biometric information of the user U1 may be input by the biometric information input unit 118.
- the biometric information of the user U1 input by the biometric information input unit 118 is not particularly limited, and may include at least one of the grip pressure of the controller by the user U1, the perspiration of the user U1, and the heartbeat of the user U1.
- the biometric information of the user U1 includes the body temperature of the user U1, the number of breaths, the number of blinks, eye movement, gaze time, pupil size, blood pressure, brain waves, body movement, body position, skin temperature, skin electrical resistance, MV (Microvibration), myoelectric potential, and SPO 2 (blood oxygen saturation) may be included.
- the output control unit 143 assumes that when the gripping pressure is smaller than the gripping pressure determination threshold value, the speech is normally performed and the accuracy of the speech recognition processing is increased, so that the text Tx ⁇ It is not necessary to output 10 reading results.
- the output control unit 143 assumes that the speech is not normally performed and the accuracy of the speech recognition processing is lowered. It is good to output the reading results.
- the output control unit 143 assumes that when the perspiration is smaller than the perspiration determination threshold, the speech is normally performed and the accuracy of the speech recognition processing is increased, so that the text Tx ⁇ It is not necessary to output 10 reading results.
- the output control unit 143 assumes that the speech is not normally performed and the accuracy of the speech recognition processing is lowered, so that the reading result of the text Tx-10 is read out. Should be output.
- the output control unit 143 assumes that the speech is normally performed and the accuracy of the speech recognition processing is increased, so that the text Tx ⁇ It is not necessary to output 10 reading results.
- the output control unit 143 assumes that the speech is not normally performed and the accuracy of the speech recognition process is lowered, so that the reading result of the text Tx-10 is read out. Should be output.
- User E1 emotion information may be obtained in any way.
- the emotion information of the user U1 may be obtained by analyzing the sound information or the input image by the output control unit 143.
- the emotion information of the user U1 is not particularly limited, and may include at least one of the joy, surprise, and anger of the user U1.
- the emotion information of the user U1 may include other emotions.
- the output control unit 143 assumes that the utterance is not normally performed and the accuracy of the speech recognition process is reduced, and thus the text Tx It is recommended to output a reading result of -10.
- the output control unit 143 assumes that the speech is normally performed and the accuracy of the speech recognition processing is increased, and thus the text Tx It is not necessary to output the reading result of -10.
- the output control unit 143 does not always have to output the reading result of the text Tx-10 to the output unit 144.
- the reading result of the text Tx-10 is output by the output unit 144.
- the output unit 144 may be controlled so that no sound is output.
- the output control unit 143 may control the output unit 144 so that the output result of the text Tx-10 is output by the output unit 144.
- the predetermined conditions are not particularly limited.
- the predetermined condition is at least one of a condition regarding the line of sight of the user U1, a condition regarding the position of the user U1, a font size (display size) of the text Tx-10, and a condition regarding the reliability of the text Tx-10.
- the position of the user U1 may be the position of the eye of the user U1
- the distance from the eye position of the user U1 to the predetermined position on the recognition result screen 133 (hereinafter also referred to as “viewing distance”) is an image. It is obtained by analyzing the image input by the input unit 110.
- the line of sight of the user U1 is also obtained by analyzing the image input by the image input unit 110.
- FIG. 11 is a diagram showing an example of the presence or absence of audio output according to the font size and viewing distance of the text Tx-10.
- the voice recognition processing is performed. The accuracy is considered lower. Therefore, in such a case, the output control unit 143 may output the reading result of the text Tx-10.
- the output control unit 143 does not have to output the reading result of the text Tx-10.
- the viewing distance to the predetermined position on the recognition result screen 133 is larger than the predetermined distance as compared to the case where the viewing distance to the predetermined position on the recognition result screen 133 is smaller than the predetermined distance, It is assumed that the necessity for the user U1 to listen to the reading result of the text Tx-10 is low. On the other hand, when the viewing distance to the predetermined position on the recognition result screen 133 is larger than the predetermined distance, it is assumed that the user U1 needs to listen to the reading result of the text Tx-10.
- the output control unit 143 may not output the reading result of the text Tx-10.
- the output control unit 143 may output the reading result of the text Tx-10.
- the predetermined position on the recognition result screen 133 is not limited, but may be the center position on the recognition result screen 133.
- the viewing distance is smaller than the viewing distance determination threshold.
- the output control unit 143 may cause the user U1 to grasp the reading result of the text Tx-10 by outputting the reading result of the text Tx-10.
- the output control unit 143 does not have to output the reading result of the text Tx-10 when the viewing distance is smaller than the viewing distance determination threshold.
- FIG. 12 is a diagram showing an example of the presence or absence of audio output according to the presence or absence of gaze retention.
- the line of sight of the user U1 exists within the recognition result screen 133 for a predetermined time, it is assumed that the necessity for the user U1 to listen to the reading result of the text Tx-10 is low.
- the line of sight of the user U1 does not exist within the recognition result screen 133 for a predetermined time, it is assumed that it is highly necessary for the user U1 to listen to the reading result of the text Tx-10.
- the output control unit 143 when the line of sight of the user U1 exists in the recognition result screen 133, the output control unit 143 should not output the reading result of the text Tx-10.
- the output control unit 143 may output the reading result of the text Tx-10.
- it is determined whether or not the line of sight exists inside the recognition result screen 133.
- it is determined whether or not the line of sight exists inside a predetermined area with reference to the recognition result screen 133. Good.
- the predetermined conditions are a condition that an operation for instructing restart of the speech recognition processing is input by the user U1, and a condition that an operation for instructing transmission of the text Tx-10 is input. At least one of them may be included.
- the operation for instructing the restart of the voice recognition process is not particularly limited, but may be a long press operation of the voice recognition process start button 132. Further, the operation for instructing the transmission of the text Tx-10 may be the above-described recognition end operation.
- the voice output mode includes the voice output speed of the reading result of the text Tx-10 and the case of including the type of output voice output before the voice output of the reading result of the text Tx-10 is described.
- the audio output mode is not limited to these.
- the voice output mode may include the magnitude of the voice output of the reading result of the text Tx-10.
- the output control unit 143 when the noise volume is larger than the noise volume determination threshold as compared with the case where the noise volume is smaller than the noise volume determination threshold, the output control unit 143 outputs the sound output of the text Tx-10 as a result of reading. It is preferable to make the user U1 understand the reading result of the text Tx-10 by increasing the value of.
- the output control unit 143 when the noise volume is smaller than the threshold for determining the noise volume as compared with the case where the noise volume is larger than the threshold for determining the noise volume, the output control unit 143 outputs the voice of the result of reading the text Tx-10. May be made smaller.
- the output control unit 143 outputs the voice output of the text Tx-10 when the utterance volume is smaller than the utterance volume determination threshold compared to the case where the utterance volume is greater than the utterance volume determination threshold. It is preferable to make the user U1 understand the result of reading the text Tx-10. On the other hand, when the utterance volume is larger than the utterance volume determination threshold value compared with the case where the utterance volume is smaller than the utterance volume determination threshold value, the output control unit 143 outputs the voice of the text Tx-10 as a result of reading out May be made smaller.
- the output control unit 143 reads out the text Tx-10 when the utterance length is shorter than the utterance length determination threshold as compared with the case where the utterance length is longer than the utterance length determination threshold. It is preferable to make the user U1 understand the reading result of the text Tx-10 by increasing the voice output of the result. On the other hand, the output control unit 143 reads out the text Tx-10 when the utterance length is longer than the utterance length determination threshold as compared to the case where the utterance length is shorter than the utterance length determination threshold. The resulting audio output may be smaller.
- the output control unit 143 determines that the text Tx-10 when the utterance clarity is smaller than the utterance clarity determination threshold value compared to when the utterance clarity is greater than the utterance clarity determination threshold value. It is preferable to increase the voice output of the reading result for the user U1 so that the user U1 can grasp the reading result of the text Tx-10. On the other hand, the output control unit 143 determines the text Tx-10 when the utterance clarity is greater than the utterance clarity determination threshold value compared to when the utterance clarity is less than the utterance clarity determination threshold value. The voice output of the reading result may be made smaller.
- the output control unit 143 outputs the voice output of the text Tx-10 when the reliability is lower than the reliability determination threshold, as compared to when the reliability is higher than the reliability determination threshold. It is preferable to make the user U1 understand the result of reading the text Tx-10. On the other hand, when the reliability is higher than the threshold for determination of reliability compared to the case where the reliability is lower than the threshold for determination of reliability, the output control unit 143 outputs the voice output of the text Tx-10 as a result of reading. May be made smaller.
- the voice output mode may include the voice quality of the reading result of the text Tx-10.
- the voice quality of the reading result of the text Tx-10 may be controlled in any way.
- the output control unit 143 may control the voice quality of the reading result of the text Tx-10 according to the sound output from an application (for example, a game application) executed by the control unit 140.
- a mode in which the text obtained as a result of the speech recognition process is input as it is is referred to as a “text input mode”.
- a mode in which a symbol converted from text obtained as a result of the speech recognition process is input is referred to as a “symbol input mode”.
- a mode in which a command converted from text obtained as a result of the speech recognition process is input is referred to as a “command input mode”.
- the voice output mode of the voice recognition processing result based on the information on the accuracy of the voice recognition processing as described above may be controlled.
- the voice output of the voice recognition processing result may or may not be performed.
- the start of the input mode is executed when a predetermined input start trigger is detected.
- the input start trigger may be the end of the voice recognition process for the sound information, or may be an operation of pressing the back button when the operation input unit 115 is provided with the back button.
- the start of the input mode may be an operation of touching a predetermined position on the touch pad when the touch pad is provided on the operation input unit 115 or the operation input unit 115 exceeding a predetermined angle. May be an operation of tilting the button, or an operation of long-pressing the button of the operation input unit 115.
- the input mode may be started when an input start trigger is detected or after a voice recognition processing result is obtained.
- FIG. 13 is a diagram for describing an outline of an example in which the input mode is started when an input start trigger is detected.
- the output control unit 143 displays the text obtained as a result of the speech recognition process on the recognition result screen 133 in the form as it is (text input mode M1).
- a command input start trigger for starting the command input mode is detected and “slanted” is spoken.
- the output control unit 143 inputs a command for converting the desired text obtained as a result of the speech recognition processing into “slash”, and recognizes the desired text after being converted to “slash” as a result of recognition. It is displayed on the screen 133 (command input mode M3).
- FIG. 13 shows an example in which switching from the text input mode to the symbol input mode and switching from the text input mode to the command input mode are performed.
- the switching of executable input modes is not limited to the example shown in FIG.
- the input mode can be switched bidirectionally between any two input modes among a text input mode, a symbol input mode, and a command input mode.
- FIG. 14 is a diagram for explaining a first outline of an example in which the input mode is started after the voice recognition processing result is obtained.
- a text input start trigger is detected and the user performs a desired utterance in the text input mode.
- the speech recognition unit 142 performs speech recognition processing for a desired utterance
- the output control unit 143 displays the text obtained as a result of the speech recognition processing on the recognition result screen 133 in the form as it is (speech recognition). Processing result M0).
- the output control unit 143 determines the text obtained as a result of the speech recognition process as it is (input completion M4).
- FIG. 15 is a diagram for explaining a second outline of an example in which the input mode is switched after the voice recognition processing result is obtained.
- a text input start trigger is detected and the user performs a desired utterance in the text input mode.
- the speech recognition unit 142 performs speech recognition processing for a desired utterance
- the output control unit 143 displays the text obtained as a result of the speech recognition processing on the recognition result screen 133 in the form as it is (speech recognition). Processing result M0).
- the output control unit 143 converts the text obtained as a result of the speech recognition processing into a symbol corresponding to the text (symbol input mode M2). Then, the output control unit 143 determines the symbol converted from the text (input completion M4).
- the input mode can be switched to the command input mode instead of the symbol input mode.
- FIG. 16 is a diagram for explaining an example in which the symbol input mode is activated after the text input mode.
- a text input start trigger is detected and the user performs a desired utterance in the text input mode.
- the output control unit 143 displays the text obtained as a result of the speech recognition process on the recognition result screen 133 in the form as it is (text input mode M1).
- the output control unit 143 automatically activates the symbol input mode when the voice recognition process is completed. Alternatively, the output control unit 143 activates the symbol input mode when a predetermined symbol input start trigger is detected.
- the symbol input start trigger is the same as the text input start trigger, but the symbol input start trigger may be different from the text input start trigger.
- the output control unit 143 converts the text “emoticon and hatena” obtained as a result of the speech recognition processing into the symbol “:)?”, And displays the symbol “:)?” On the recognition result screen 133.
- (Symbol input mode M2). :) is an emoticon representing a smile.
- the output control unit 143 determines the text and the symbol “:)?” Obtained as a result of the voice recognition process (input completion M4).
- the voice recognition end trigger is the same as the text input start trigger, but the voice recognition end trigger may be different from the text input start trigger.
- FIG. 17 is a diagram for explaining an example in which the symbol input mode and the command input mode are started after the text input mode.
- the text obtained as a result of the speech recognition process is displayed on the recognition result screen 133 in the form as it is (text input mode M1), and the text “ A symbol “:)?” Converted from “emoticon and Hatena” is displayed on the recognition result screen 133 (symbol input mode M2).
- the output control unit 143 automatically activates the command input mode when the voice recognition process is completed.
- the output control unit 143 activates the command input mode when a predetermined command input start trigger is detected.
- the command input start trigger is the same as the text input start trigger, but the command input start trigger may be different from the text input start trigger.
- the output control unit 143 inputs a command for converting the desired text and the symbol “:)?” Obtained as a result of the speech recognition processing into “inclined”, and after being converted into “inclined” Is displayed on the recognition result screen 133 (command input mode M3). Thereafter, when the output control unit 143 detects a predetermined voice recognition end trigger, the output control unit 143 determines a desired text and a “slash” of the symbol “:)?” Obtained as a result of the voice recognition process (input completion M4). .
- FIG. 18 and 19 are diagrams for explaining an example in which the text input mode or the symbol input mode is first activated.
- a text input start trigger is detected and the user utters a desired utterance in the text input mode.
- the speech recognition unit 142 performs speech recognition processing for a desired utterance
- the output control unit 143 displays the text obtained as a result of the speech recognition processing on the recognition result screen 133 in the form as it is (text input).
- Mode M1 the text input start trigger
- the output control unit 143 converts the text obtained as a result of the speech recognition processing into a symbol corresponding to the text (symbol input mode M2).
- symbol input mode M2 the output control unit 143 inputs a command corresponding to the text obtained as a result of the speech recognition process.
- the symbol input start trigger is detected and the user performs a desired utterance in the symbol input mode.
- the speech recognition unit 142 performs speech recognition processing for a desired utterance
- the output control unit 143 converts the text obtained as a result of the speech recognition processing into a symbol, and displays the symbol on the recognition result screen 133. (Symbol input mode M2).
- the speech recognition unit 142 performs speech recognition processing for the desired utterance, and the output control unit 143 performs speech recognition processing.
- the resulting text is displayed on the recognition result screen 133 (text input mode M1).
- the output control unit 143 detects a command input start trigger, the output control unit 143 displays the symbol after being converted to “slash” on the recognition result screen 133 (command input mode M3).
- the output control unit 143 may control whether or not to automatically activate the symbol input mode based on the contents of messages (voice recognition processing results) transmitted and received in the past.
- FIG. 20 is a diagram for describing an example in which the symbol input mode is automatically activated based on the contents of messages transmitted and received in the past. As shown in FIG. 20, the message transmitted / received in the past includes four symbols (two emoticons and two exclamation marks), and the possibility of the next symbol input is performed. Is assumed to be high.
- the speech recognition unit 142 performs speech recognition processing for a desired utterance, and the output control unit 143 displays the text obtained as a result of the speech recognition processing on the recognition result screen 133 in the form as it is (text input). Mode M1). Subsequently, the output control unit 143 estimates that there is a high possibility that the next symbol input will be performed based on messages transmitted and received in the past, and automatically activates the symbol input mode.
- the output control unit 143 converts the text “emoticon and hatena” obtained as a result of the speech recognition processing into the symbol “:)?”, And displays the symbol “:)?” On the recognition result screen 133. (Symbol input mode M2). Thereafter, when the output control unit 143 detects a predetermined voice recognition end trigger, the output control unit 143 determines the text and the symbol “:)?” Obtained as a result of the voice recognition process (input completion M4).
- the voice recognition end trigger is the same as the text input start trigger, but the voice recognition end trigger may be different from the text input start trigger.
- FIG. 21 is a diagram for explaining an example in which the symbol input mode is not automatically activated based on the contents of messages transmitted and received in the past.
- a message transmitted / received in the past includes only one symbol (only one exclamation mark is included as a symbol), and the symbol can be input next.
- the case is estimated to be low.
- the speech recognition unit 142 performs speech recognition processing for a desired utterance, and the output control unit 143 displays the text obtained as a result of the speech recognition processing on the recognition result screen 133 in the form as it is (text input). Mode M1). Subsequently, the output control unit 143 estimates that there is a low possibility that the next symbol input will be performed based on messages transmitted and received in the past, and does not automatically activate the symbol input mode.
- the output control unit 143 determines the text obtained as a result of the voice recognition process (input completion M5).
- the voice recognition end trigger is the same as the text input start trigger, but the voice recognition end trigger may be different from the text input start trigger.
- the output control unit 143 converts the text “emoticon and hatena” obtained as a result of the speech recognition processing into the symbol “:)?”, And displays the symbol “:)?” On the recognition result screen 133. (Symbol input mode M2). Thereafter, when the output control unit 143 detects a predetermined voice recognition end trigger, the output control unit 143 determines the text and the symbol “:)?” Obtained as a result of the voice recognition process (input completion M4).
- the voice recognition end trigger is the same as the text input start trigger, but the voice recognition end trigger may be different from the text input start trigger.
- the output control unit 143 may determine whether or not to automatically activate the activation input mode depending on whether or not the amount of symbols included in messages transmitted and received during a predetermined period exceeds a threshold value.
- the output control unit 143 may determine whether to automatically activate the symbol input mode by applying statistical processing such as machine learning to messages transmitted and received during a predetermined period.
- the output control unit 143 determines whether to automatically activate the symbol input mode based on the contents of the transmitted / received message. However, the output control unit 143 may not determine whether to automatically activate the symbol input mode based on the contents of both the transmitted message and the received message. Specifically, the output control unit 143 may determine whether to automatically activate the symbol input mode based on only the content of the transmitted message, or based only on the content of the received message. It may be determined whether or not the symbol input mode is automatically activated.
- the output control unit 143 may control whether or not to automatically start the command input mode based on the operation frequency of the controller of the game machine as an example of the operation input unit 115.
- FIG. 22 is a diagram for explaining an example of controlling whether to automatically start the command input mode based on the operation frequency of the controller. As shown in FIG. 22, it is assumed that the controller operation frequency in the latest T seconds exceeds the threshold value and the controller operation frequency in the latest T seconds does not exceed the threshold value.
- the speech recognition unit 142 performs speech recognition processing for a desired utterance, and the output control unit 143 displays the text obtained as a result of the speech recognition processing on the recognition result screen 133 in the form as it is (text input). Mode M1). Subsequently, the output control unit 143 activates the symbol input mode when a symbol input start trigger is detected or automatically.
- the output control unit 143 converts the text “emoticon and hatena” obtained as a result of the speech recognition processing into the symbol “:)?”, And displays the symbol “:)?” On the recognition result screen 133. (Symbol input mode M2).
- the output control unit 143 determines that it is difficult for the user to operate the controller when the controller operation frequency for the latest T seconds exceeds the threshold, and automatically activates the command input mode.
- the output control unit 143 inputs a command for converting the desired text and the symbol “:)?” Obtained as a result of the speech recognition processing into “slash”, and after the conversion to the italic.
- the output control unit 143 determines that it is easy for the user to operate the controller when the controller operation frequency for the last T seconds does not exceed the threshold value, and does not automatically start the command input mode.
- the text and the symbol “:)?” Obtained as a result of the voice recognition process are determined (input completion M4).
- the output control unit 143 may activate the command input mode.
- the output control unit 143 may determine whether to automatically start the command input mode based on game scene information. For example, when the game scene information indicates that the game is being loaded, the output control unit 143 does not need to activate the command input mode automatically because the user does not have to concentrate on the game. On the other hand, the output control unit 143 may automatically start the command input mode because the user is presumed to be concentrated in the game when the scene information of the game indicates that the battle is in progress.
- the output control unit 143 may determine whether to automatically start the command input mode based on the user's concentration level. For example, the output control unit 143 may automatically start the command input mode when the concentration level exceeds a threshold value. On the other hand, the output control unit 143 may not automatically activate the command input mode when the concentration level does not exceed the threshold value.
- the degree of concentration may be estimated based on the user's line of sight, or may be estimated based on the user's biological information (for example, sweating, heartbeat, etc.).
- the output control unit 143 may control whether to automatically activate the symbol input mode based on the emotion information of the user.
- FIG. 23 is a diagram for explaining an example of controlling whether to automatically activate the symbol input mode based on user emotion information. As shown in FIG. 23, it is assumed that the user's emotion is strong and the user's emotion is weak.
- the speech recognition unit 142 performs speech recognition processing for a desired utterance
- the output control unit 143 displays the text obtained as a result of the speech recognition processing on the recognition result screen 133 in the form as it is (text input). Mode M1).
- the output control unit 143 determines that the user's emotion is stronger than the threshold value, the output control unit 143 estimates that there is a high possibility of the next symbol input, and automatically activates the symbol input mode.
- the output control unit 143 converts the text “emoticon and hatena” obtained as a result of the speech recognition processing into the symbol “:)?”, And displays the symbol “:)?” On the recognition result screen 133. (Symbol input mode M2).
- the output control unit 143 determines the text and the symbol “:”? ”Obtained as a result of the voice recognition process (input completion M4).
- the voice recognition end trigger is the same as the text input start trigger, but the voice recognition end trigger may be different from the text input start trigger.
- the output control unit 143 determines that the user's emotion is weaker than the threshold value, the output control unit 143 estimates that the possibility of the next symbol input is low, and does not automatically activate the symbol input mode. Subsequently, when the output control unit 143 detects a predetermined speech recognition end trigger, the output control unit 143 determines the text obtained as a result of the speech recognition process (input completion M5).
- the voice recognition end trigger is the same as the text input start trigger, but the voice recognition end trigger may be different from the text input start trigger.
- the output control unit 143 may determine the emotion information of the user based on the analysis result of the sound information collected by the sound collection unit 120. For example, the output control unit 143 may determine that the user's emotion is stronger than the threshold when the intonation conversion of the sound information collected by the sound collection unit 120 is larger than the threshold. On the other hand, when the intonation conversion of the sound information collected by the sound collection unit 120 is smaller than the threshold, the output control unit 143 may determine that the user's emotion is weaker than the threshold.
- the output control unit 143 may determine that the user's emotion is stronger than the threshold when the volume change of the sound information collected by the sound collection unit 120 is larger than the threshold. On the other hand, when the volume change of the sound information collected by the sound collection unit 120 is smaller than the threshold, the output control unit 143 may determine that the user's emotion is weaker than the threshold.
- the output control unit 143 may determine the emotion information of the user based on the analysis result of the image input by the image input unit 110. For example, when the facial expression analyzed from the image input by the image input unit 110 indicates a strong emotion, the output control unit 143 may determine that the user's emotion is stronger than the threshold value. On the other hand, when the facial expression analyzed from the image input by the image input unit 110 indicates a weak emotion, the output control unit 143 may determine that the user's emotion is weaker than the threshold.
- FIG. 24 is a view showing a modification of the utterance screen 135.
- the utterance screen 135X according to the modification includes “Icon” indicating a state where a symbol is input and “Text” indicating a state where a text is input.
- FIG. 25 is a diagram illustrating an example of the utterance screen 135X when text input is performed based on the user's utterance.
- the output control unit 143 displays the text “Good morning” obtained as a result of the speech recognition processing on the recognition result screen 133.
- the output control unit 143 may expand and contract the indicator 137 to which the character string “Text” is attached according to the utterance volume.
- FIG. 25 is a diagram illustrating an example of the utterance screen 135X when text input is performed based on the user's utterance.
- the output control unit 143 displays the text obtained as the speech recognition processing result on the recognition result screen 133.
- the output control unit 143 may expand or contract the indicator 137 at a position corresponding to the character string position “Text” according to the utterance volume.
- FIG. 26 is a diagram showing an example of an utterance screen 135Y when a symbol is input based on the user's utterance.
- the output control unit 143 converts the newly obtained text “emoticon and hatena” as a result of the speech recognition processing into a symbol and displays it on the recognition result screen 133. Further, in a state where a symbol is input, the output control unit 143 may expand or contract the indicator 138 at a position corresponding to the character string position “Icon” according to the utterance volume.
- the user can intuitively grasp the current input mode by changing the extending direction between the indicator 137 in the state where the text is input and the indicator 138 in the state where the symbol is input. Is possible. Furthermore, by making the color of the indicator 137 different from the color of the indicator 138, the user can intuitively grasp the current input mode.
- FIG. 27 is a block diagram illustrating a hardware configuration example of the information processing system 10 according to the embodiment of the present disclosure.
- the information processing system 10 includes a CPU (Central Processing unit) 901, a ROM (Read Only Memory) 903, and a RAM (Random Access Memory) 905.
- the information processing system 10 may also include a host bus 907, a bridge 909, an external bus 911, an interface 913, an input device 915, an output device 917, a storage device 919, a drive 921, a connection port 923, and a communication device 925.
- the information processing system 10 may include an imaging device 933 and a sensor 935 as necessary.
- the information processing system 10 may include a processing circuit called DSP (Digital Signal Processor) or ASIC (Application Specific Integrated Circuit) instead of or in addition to the CPU 901.
- DSP Digital Signal Processor
- ASIC Application Specific Integrated Circuit
- the CPU 901 functions as an arithmetic processing unit and a control unit, and controls all or part of the operation in the information processing system 10 according to various programs recorded in the ROM 903, the RAM 905, the storage device 919, or the removable recording medium 927.
- the ROM 903 stores programs and calculation parameters used by the CPU 901.
- the RAM 905 temporarily stores programs used in the execution of the CPU 901, parameters that change as appropriate during the execution, and the like.
- the CPU 901, the ROM 903, and the RAM 905 are connected to each other by a host bus 907 configured by an internal bus such as a CPU bus. Further, the host bus 907 is connected to an external bus 911 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 909.
- PCI Peripheral Component Interconnect / Interface
- the input device 915 is a device operated by the user, such as a mouse, a keyboard, a touch panel, a button, a switch, and a lever.
- the input device 915 may include a microphone that detects the user's voice.
- the input device 915 may be, for example, a remote control device using infrared rays or other radio waves, or may be an external connection device 929 such as a mobile phone that supports the operation of the information processing system 10.
- the input device 915 includes an input control circuit that generates an input signal based on information input by the user and outputs the input signal to the CPU 901. The user operates the input device 915 to input various data to the information processing system 10 and instruct processing operations.
- An imaging device 933 which will be described later, can also function as an input device by imaging a user's hand movement, a user's finger, and the like. At this time, the pointing position may be determined according to the movement of the hand or the direction of the finger.
- the output device 917 is a device that can notify the user of the acquired information visually or audibly.
- the output device 917 is, for example, a display device such as an LCD (Liquid Crystal Display), a PDP (Plasma Display Panel), an organic EL (Electro-Luminescence) display, a projector, an audio output device such as a hologram display device, a speaker and headphones, As well as a printer device.
- the output device 917 outputs the result obtained by the processing of the information processing system 10 as a video such as text or an image, or outputs it as a voice such as voice or sound.
- the output device 917 may include a light or the like to brighten the surroundings.
- the storage device 919 is a data storage device configured as an example of a storage unit of the information processing system 10.
- the storage device 919 includes, for example, a magnetic storage device such as an HDD (Hard Disk Drive), a semiconductor storage device, an optical storage device, or a magneto-optical storage device.
- the storage device 919 stores programs executed by the CPU 901, various data, various data acquired from the outside, and the like.
- the drive 921 is a reader / writer for a removable recording medium 927 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and is built in or externally attached to the information processing system 10.
- the drive 921 reads information recorded on the attached removable recording medium 927 and outputs the information to the RAM 905.
- the drive 921 writes a record in the attached removable recording medium 927.
- the connection port 923 is a port for directly connecting a device to the information processing system 10.
- the connection port 923 can be, for example, a USB (Universal Serial Bus) port, an IEEE 1394 port, a SCSI (Small Computer System Interface) port, or the like.
- the connection port 923 may be an RS-232C port, an optical audio terminal, an HDMI (registered trademark) (High-Definition Multimedia Interface) port, or the like.
- Various data can be exchanged between the information processing system 10 and the external connection device 929 by connecting the external connection device 929 to the connection port 923.
- the communication device 925 is a communication interface configured with, for example, a communication device for connecting to the communication network 931.
- the communication device 925 can be, for example, a communication card for wired or wireless LAN (Local Area Network), Bluetooth (registered trademark), or WUSB (Wireless USB).
- the communication device 925 may be a router for optical communication, a router for ADSL (Asymmetric Digital Subscriber Line), or a modem for various communication.
- the communication device 925 transmits and receives signals and the like using a predetermined protocol such as TCP / IP with the Internet and other communication devices, for example.
- the communication network 931 connected to the communication device 925 is a wired or wireless network, such as the Internet, a home LAN, infrared communication, radio wave communication, or satellite communication.
- the imaging device 933 uses various members such as an imaging element such as a CCD (Charge Coupled Device) or CMOS (Complementary Metal Oxide Semiconductor), and a lens for controlling the imaging of a subject image on the imaging element. It is an apparatus that images a real space and generates a captured image.
- the imaging device 933 may capture a still image or may capture a moving image.
- the sensor 935 is various sensors such as an acceleration sensor, a gyro sensor, a geomagnetic sensor, an optical sensor, and a sound sensor.
- the sensor 935 obtains information related to the state of the information processing system 10 such as the posture of the information processing system 10, and information related to the surrounding environment of the information processing system 10 such as brightness and noise around the information processing system 10. To do.
- the sensor 935 may include a GPS sensor that receives a GPS (Global Positioning System) signal and measures the latitude, longitude, and altitude of the apparatus.
- GPS Global Positioning System
- the information acquisition unit 141 that acquires information related to the accuracy of the speech recognition process for the sound information based on the sound collection, and the information based on the information related to the accuracy of the speech recognition process
- An information processing apparatus (control unit) 140 is provided, which includes an output control unit 143 that controls the voice output mode of the recognition processing result. According to this configuration, it is possible to allow the user to grasp the accuracy of the speech recognition process by the speech output mode of the text reading result.
- the voice output mode may be controlled differently in one sentence (or in one phrase).
- the output control unit 143 may increase the voice output speed at the beginning of a sentence that is likely to be mistaken for voice recognition processing higher than the voice output speed at other parts.
- the output control unit 143 may omit reading out all or part of the speech recognition processing result when the speech recognition processing result becomes longer than a certain length.
- the information processing system 10 may be a system in which the display unit 130 does not exist (for example, a neck-mounted device).
- the information processing system 10 includes a game machine and a television receiver, and the user U1 performs online chat using a chat application during game play.
- the hardware configuration of the information processing system 10 is not limited to this example.
- the information processing system 10 may be a wearable device (for example, a wristwatch, an HMD, a neck-mounted device, etc.), a stationary device used at home, or an in-vehicle device. It may be.
- the position of each component is not particularly limited as long as the operation of the information processing system 10 described above is realized.
- the image input unit 110, the operation input unit 115, the biological information input unit 118, the sound collection unit 120, the communication unit 125, the display unit 130, the sound output unit 150, and the control unit 140 are connected via a network. You may provide in the mutually different apparatus connected.
- the control unit 140 corresponds to a server such as a web server or a cloud server, and includes an image input unit 110, an operation input unit 115, a biological information input unit 118, a sound collection unit 120, a communication unit 125,
- the display unit 130 and the sound output unit 150 may correspond to a client connected to the server via a network.
- control unit 140 may not be accommodated in the same device.
- some of the information acquisition unit 141, the voice recognition unit 142, the output control unit 143, and the output unit 144 may exist in a device different from the control unit 140.
- the voice recognition unit 142 and the output control unit 143 may exist on a different server from the control unit 140 including the information acquisition unit 141 and the output unit 144.
- An information acquisition unit for acquiring information related to accuracy of voice recognition processing for sound information based on sound collection;
- An output control unit that controls a voice output mode of a voice recognition processing result based on information on the accuracy of the voice recognition processing;
- An information processing apparatus comprising: (2)
- the information related to the accuracy of the voice recognition process includes information related to the user's utterance included in the sound information.
- the information processing apparatus according to (1) (3)
- the information related to the user's utterance includes at least one of the user's utterance volume, the user's utterance clarity, and the user's utterance length included in the sound information.
- the information related to the accuracy of the voice recognition processing includes information related to noise corresponding to the user's utterance included in the sound information.
- the information on the noise includes a volume of noise included in the sound information.
- the information regarding the accuracy of the speech recognition processing includes the reliability of the speech recognition processing result,
- the output control unit controls the audio output mode based on information about a user.
- the information on the user is at least one of the user behavior information, the user posture information, the setting information by the user, the environment information around the user, the biological information of the user, and the emotion information of the user.
- the information processing apparatus includes, The information processing apparatus according to (7). (9) The information related to the accuracy of the voice recognition process includes the amount of the voice recognition process result.
- the voice output mode includes a type of output voice that is output before voice output of the voice recognition processing result.
- the voice output mode includes voice quality of the voice recognition processing result, The information processing apparatus according to any one of (1) to (14).
- the output control unit controls the output unit so that the voice recognition processing result is not output by the output unit when a predetermined condition is satisfied, The information processing apparatus according to any one of (1) to (15).
- the predetermined condition includes at least one of a condition relating to a user's line of sight, a condition relating to a user's position, a display size of the voice recognition processing result, and a condition relating to reliability of the voice recognition processing result.
- the predetermined condition includes a condition that an operation for instructing restart of the voice recognition processing is input by a user, and a condition that an operation for instructing transmission of the voice recognition processing result is input. Including at least one of them, The information processing apparatus according to (16) or (17). (19) Obtaining information on accuracy of speech recognition processing for sound information based on sound collection; Controlling a voice output mode of a voice recognition processing result based on information on accuracy of the voice recognition processing by a processor; Including an information processing method.
- Computer An information acquisition unit for acquiring information related to accuracy of voice recognition processing for sound information based on sound collection; An output control unit that controls a voice output mode of a voice recognition processing result based on information on the accuracy of the voice recognition processing; A program for causing an information processing apparatus to function.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
Description
1.本開示の実施形態
1.1.システム構成例
1.2.機能構成例
1.3.情報処理システムの機能詳細
1.4.ハードウェア構成例
2.むすび
[1.1.システム構成例]
まず、図面を参照しながら本開示の一実施形態に係る通信システムの構成例について説明する。図2は、本開示の一実施形態に係る通信システムの構成例を示す図である。図2に示したように、本実施形態に係る通信システムは、情報処理システム10-1および情報処理システム10-2を備える。情報処理システム10-1および情報処理システム10-2それぞれは、画像入力部110、操作入力部115、生体情報入力部118、集音部120、表示部130、音出力部150および情報処理装置(以下、「制御部」とも言う。)140を有している。
続いて、本実施形態に係る情報処理システム10の機能構成例について説明する。図1は、本実施形態に係る情報処理システム10の機能構成例を示すブロック図である。図1に示したように、情報処理システム10は、画像入力部110と、操作入力部115と、生体情報入力部118と、集音部120と、通信部125と、表示部130と、音出力部150と、制御部140とを備える。
続いて、情報処理システム10の機能詳細について説明する。図3は、情報処理システム10の概要を説明するための図である。図3を参照すると、制御部140によって再生された映像が表示される映像表示画面131が表示部130に存在する。ここでは、制御部140がゲーム機である場合を想定しているため、映像表示画面131に表示される映像は、ゲームアプリケーションに含まれる映像である。
ここで、ユーザU1はテキストTx-10「Et's play game.」の読み上げ結果を聴くだけでは、音声認識処理がどのような精度で行われたかを把握するのが困難である。具体的には、テキストTx-10「Et's play game.」はユーザU1の発話内容である「Let's play game.」と異なってしまっているが、ユーザU1は音声認識処理の精度の低さを把握するのが困難である。特に、ユーザU1が映像表示画面131に集中しているときには、音声認識処理が正常に行われたか否かを確認する作業は煩わしい。そこで、音声認識処理結果を聴くユーザU1に対して音声認識処理の精度を把握させることが可能な技術が提供されることが望まれる。
ところで、上記においては、音声認識処理結果として得られるテキストをそのままの形式で入力する場合について説明した。しかし、ユーザは、音声認識処理の結果として得られるテキストを他の形式に変換してから入力したいと考える場合もあり得る。例えば、ユーザは、音声認識処理の結果として得られるテキストから変換された記号を入力したいと考える場合もあり得る。また、ユーザは、音声認識処理の結果として得られるテキストから変換されたコマンドを入力したいと考える場合もあり得る。
次に、図27を参照して、本開示の実施形態に係る情報処理システム10のハードウェア構成について説明する。図27は、本開示の実施形態に係る情報処理システム10のハードウェア構成例を示すブロック図である。
以上説明したように、本開示の実施形態によれば、集音に基づく音情報に対する音声認識処理の精度に関する情報を取得する情報取得部141と、音声認識処理の精度に関する情報に基づいて、音声認識処理結果の音声出力態様を制御する出力制御部143と、を備える、情報処理装置(制御部)140が提供される。かかる構成によれば、テキストの読み上げ結果の音声出力態様によって、音声認識処理の精度をユーザに把握させることが可能となる。
(1)
集音に基づく音情報に対する音声認識処理の精度に関する情報を取得する情報取得部と、
前記音声認識処理の精度に関する情報に基づいて、音声認識処理結果の音声出力態様を制御する出力制御部と、
を備える、情報処理装置。
(2)
前記音声認識処理の精度に関する情報は、前記音情報に含まれるユーザの発話に関する情報を含む、
前記(1)に記載の情報処理装置。
(3)
前記ユーザの発話に関する情報は、前記音情報に含まれる前記ユーザの発話音量、前記ユーザの発話の明瞭さ、および、前記ユーザの発話長さのうち少なくともいずれか一つを含む、
前記(2)に記載の情報処理装置。
(4)
前記音声認識処理の精度に関する情報は、前記音情報に含まれるユーザの発話に対応するノイズに関する情報を含む、
前記(1)~(3)のいずれか一項に記載の情報処理装置。
(5)
前記ノイズに関する情報は、前記音情報に含まれるノイズの音量を含む、
前記(4)に記載の情報処理装置。
(6)
前記音声認識処理の精度に関する情報は、前記音声認識処理結果の信頼度を含む、
前記(1)~(5)のいずれか一項に記載の情報処理装置。
(7)
前記出力制御部は、ユーザに関する情報に基づいて、前記音声出力態様を制御する、
前記(6)に記載の情報処理装置。
(8)
前記ユーザに関する情報は、前記ユーザの行動情報、前記ユーザの姿勢情報、前記ユーザによる設定情報、前記ユーザの周囲の環境情報、前記ユーザの生体情報および前記ユーザの感情情報のうち少なくともいずれか一つを含む、
前記(7)に記載の情報処理装置。
(9)
前記音声認識処理の精度に関する情報は、前記音声認識処理結果の量を含む、
前記(1)~(8)のいずれか一項に記載の情報処理装置。
(10)
前記出力制御部は、前記音声認識処理結果が利用されるコンテンツの種類に基づいて、前記音声出力態様を制御する、
前記(1)~(9)のいずれか一項に記載の情報処理装置。
(11)
前記出力制御部は、前記音声認識処理の実行頻度に基づいて、前記音声出力態様を制御する、
前記(1)~(10)のいずれか一項に記載の情報処理装置。
(12)
前記音声出力態様は、前記音声認識処理結果の音声出力速度を含む、
前記(1)~(11)のいずれか一項に記載の情報処理装置。
(13)
前記音声出力態様は、前記音声認識処理結果の音声出力の大きさを含む、
前記(1)~(12)のいずれか一項に記載の情報処理装置。
(14)
前記音声出力態様は、前記音声認識処理結果の音声出力前に出力される出力音声の種類を含む、
前記(1)~(13)のいずれか一項に記載の情報処理装置。
(15)
前記音声出力態様は、前記音声認識処理結果の声質を含む、
前記(1)~(14)のいずれか一項に記載の情報処理装置。
(16)
前記出力制御部は、所定の条件が満たされた場合に、前記音声認識処理結果が出力部によって音声出力されないように前記出力部を制御する、
前記(1)~(15)のいずれか一項に記載の情報処理装置。
(17)
前記所定の条件は、ユーザの視線に関する条件、ユーザの位置に関する条件、前記音声認識処理結果の表示サイズ、および、前記音声認識処理結果の信頼度に関する条件のうち少なくともいずれか一つを含む、
前記(16)に記載の情報処理装置。
(18)
前記所定の条件は、ユーザによって前記音声認識処理の再起動を指示するための操作が入力されたという条件、および、前記音声認識処理結果の送信を指示するための操作が入力されたという条件のうち少なくともいずれか一つを含む、
前記(16)または(17)に記載の情報処理装置。
(19)
集音に基づく音情報に対する音声認識処理の精度に関する情報を取得することと、
プロセッサにより、前記音声認識処理の精度に関する情報に基づいて、音声認識処理結果の音声出力態様を制御することと、
を含む、情報処理方法。
(20)
コンピュータを、
集音に基づく音情報に対する音声認識処理の精度に関する情報を取得する情報取得部と、
前記音声認識処理の精度に関する情報に基づいて、音声認識処理結果の音声出力態様を制御する出力制御部と、
を備える情報処理装置として機能させるためのプログラム。
110 画像入力部
115 操作入力部
118 生体情報入力部
120 集音部
125 通信部
130 表示部
131 映像表示画面
132 音声認識処理開始ボタン
133 認識結果画面
134 チャット画面
135 発話画面
136 音声認識処理終了ボタン
140 情報処理装置(制御部)
141 情報取得部
142 音声認識部
143 出力制御部
144 出力部
150 音出力部
U1 ユーザ
Claims (20)
- 集音に基づく音情報に対する音声認識処理の精度に関する情報を取得する情報取得部と、
前記音声認識処理の精度に関する情報に基づいて、音声認識処理結果の音声出力態様を制御する出力制御部と、
を備える、情報処理装置。 - 前記音声認識処理の精度に関する情報は、前記音情報に含まれるユーザの発話に関する情報を含む、
請求項1に記載の情報処理装置。 - 前記ユーザの発話に関する情報は、前記音情報に含まれる前記ユーザの発話音量、前記ユーザの発話の明瞭さ、および、前記ユーザの発話長さのうち少なくともいずれか一つを含む、
請求項2に記載の情報処理装置。 - 前記音声認識処理の精度に関する情報は、前記音情報に含まれるユーザの発話に対応するノイズに関する情報を含む、
請求項1に記載の情報処理装置。 - 前記ノイズに関する情報は、前記音情報に含まれるノイズの音量を含む、
請求項4に記載の情報処理装置。 - 前記音声認識処理の精度に関する情報は、前記音声認識処理結果の信頼度を含む、
請求項1に記載の情報処理装置。 - 前記出力制御部は、ユーザに関する情報に基づいて、前記音声出力態様を制御する、
請求項6に記載の情報処理装置。 - 前記ユーザに関する情報は、前記ユーザの行動情報、前記ユーザの姿勢情報、前記ユーザによる設定情報、前記ユーザの周囲の環境情報、前記ユーザの生体情報および前記ユーザの感情情報のうち少なくともいずれか一つを含む、
請求項7に記載の情報処理装置。 - 前記音声認識処理の精度に関する情報は、前記音声認識処理結果の量を含む、
請求項1に記載の情報処理装置。 - 前記出力制御部は、前記音声認識処理結果が利用されるコンテンツの種類に基づいて、前記音声出力態様を制御する、
請求項1に記載の情報処理装置。 - 前記出力制御部は、前記音声認識処理の実行頻度に基づいて、前記音声出力態様を制御する、
請求項1に記載の情報処理装置。 - 前記音声出力態様は、前記音声認識処理結果の音声出力速度を含む、
請求項1に記載の情報処理装置。 - 前記音声出力態様は、前記音声認識処理結果の音声出力の大きさを含む、
請求項1に記載の情報処理装置。 - 前記音声出力態様は、前記音声認識処理結果の音声出力前に出力される出力音声の種類を含む、
請求項1に記載の情報処理装置。 - 前記音声出力態様は、前記音声認識処理結果の声質を含む、
請求項1に記載の情報処理装置。 - 前記出力制御部は、所定の条件が満たされた場合に、前記音声認識処理結果が出力部によって音声出力されないように前記出力部を制御する、
請求項1に記載の情報処理装置。 - 前記所定の条件は、ユーザの視線に関する条件、ユーザの位置に関する条件、前記音声認識処理結果の表示サイズ、および、前記音声認識処理結果の信頼度に関する条件のうち少なくともいずれか一つを含む、
請求項16に記載の情報処理装置。 - 前記所定の条件は、ユーザによって前記音声認識処理の再起動を指示するための操作が入力されたという条件、および、前記音声認識処理結果の送信を指示するための操作が入力されたという条件のうち少なくともいずれか一つを含む、
請求項16に記載の情報処理装置。 - 集音に基づく音情報に対する音声認識処理の精度に関する情報を取得することと、
プロセッサにより、前記音声認識処理の精度に関する情報に基づいて、音声認識処理結果の音声出力態様を制御することと、
を含む、情報処理方法。 - コンピュータを、
集音に基づく音情報に対する音声認識処理の精度に関する情報を取得する情報取得部と、
前記音声認識処理の精度に関する情報に基づいて、音声認識処理結果の音声出力態様を制御する出力制御部と、
を備える情報処理装置として機能させるためのプログラム。
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2017563687A JPWO2017130486A1 (ja) | 2016-01-28 | 2016-10-24 | 情報処理装置、情報処理方法およびプログラム |
| US16/069,264 US20190019512A1 (en) | 2016-01-28 | 2016-10-24 | Information processing device, method of information processing, and program |
| CN201680079643.7A CN108475507A (zh) | 2016-01-28 | 2016-10-24 | 信息处理设备、信息处理方法和程序 |
| EP16888071.4A EP3410433A4 (en) | 2016-01-28 | 2016-10-24 | INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING PROCESS AND PROGRAM |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2016013899 | 2016-01-28 | ||
| JP2016-013899 | 2016-01-28 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2017130486A1 true WO2017130486A1 (ja) | 2017-08-03 |
Family
ID=59397756
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2016/081470 Ceased WO2017130486A1 (ja) | 2016-01-28 | 2016-10-24 | 情報処理装置、情報処理方法およびプログラム |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US20190019512A1 (ja) |
| EP (1) | EP3410433A4 (ja) |
| JP (1) | JPWO2017130486A1 (ja) |
| CN (1) | CN108475507A (ja) |
| WO (1) | WO2017130486A1 (ja) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019058673A1 (ja) * | 2017-09-21 | 2019-03-28 | ソニー株式会社 | 情報処理装置、情報処理端末、情報処理方法、および、プログラム |
| JP2020507165A (ja) * | 2017-11-21 | 2020-03-05 | ジョンアン インフォメーション テクノロジー サービシズ カンパニー リミテッド | データ可視化のための情報処理方法及び装置 |
| JP2020197973A (ja) * | 2019-06-04 | 2020-12-10 | コニカミノルタ株式会社 | ジョブ処理システム、ジョブ制御装置、音声通知方法、およびコンピュータプログラム |
| WO2023286249A1 (ja) * | 2021-07-15 | 2023-01-19 | 日本電信電話株式会社 | コミュニケーション支援システム、コミュニケーション支援方法およびプログラム |
| JP2023546989A (ja) * | 2020-10-08 | 2023-11-08 | モジュレイト インク. | コンテンツモデレーションのためのマルチステージ適応型システム |
| US12341619B2 (en) | 2022-06-01 | 2025-06-24 | Modulate, Inc. | User interface for content moderation of voice chat |
| US12412588B2 (en) | 2017-05-24 | 2025-09-09 | Modulate, Inc. | System and method for creating timbres |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102691889B1 (ko) * | 2016-07-27 | 2024-08-06 | 삼성전자주식회사 | 전자 장치 및 그의 음성 인식 방법 |
| US10777201B2 (en) * | 2016-11-04 | 2020-09-15 | Microsoft Technology Licensing, Llc | Voice enabled bot platform |
| KR20190091265A (ko) * | 2016-12-05 | 2019-08-05 | 소니 주식회사 | 정보 처리 장치, 정보 처리 방법, 및 정보 처리 시스템 |
| US10728616B2 (en) * | 2017-04-19 | 2020-07-28 | Intel Corporation | User interest-based enhancement of media quality |
| CN109147784B (zh) * | 2018-09-10 | 2021-06-08 | 百度在线网络技术(北京)有限公司 | 语音交互方法、设备以及存储介质 |
| CN111199732B (zh) * | 2018-11-16 | 2022-11-15 | 深圳Tcl新技术有限公司 | 一种基于情感的语音交互方法、存储介质及终端设备 |
| EP3901947A4 (en) * | 2018-12-19 | 2022-02-23 | Sony Group Corporation | INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD AND PROGRAM |
| CN110047487B (zh) * | 2019-06-05 | 2022-03-18 | 广州小鹏汽车科技有限公司 | 车载语音设备的唤醒方法、装置、车辆以及机器可读介质 |
| US20210090558A1 (en) * | 2019-09-24 | 2021-03-25 | Audio Analytic Ltd | Controlling a user interface |
| CN117693790A (zh) * | 2021-07-27 | 2024-03-12 | 高通股份有限公司 | 使用上下文信息和用户情绪的话音或语音识别 |
| CN118356301A (zh) * | 2024-06-18 | 2024-07-19 | 中国人民解放军总医院 | 一种能智能输出诊断策略的急救包 |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS62254194A (ja) * | 1986-04-28 | 1987-11-05 | 日本電気株式会社 | 音声認識応答装置 |
| JPS62267800A (ja) * | 1986-05-16 | 1987-11-20 | 株式会社日立製作所 | 音声認識制御方式 |
| JPH02109100A (ja) * | 1988-10-19 | 1990-04-20 | Fujitsu Ltd | 音声入力装置 |
| JPH08335094A (ja) * | 1995-06-08 | 1996-12-17 | Nippon Telegr & Teleph Corp <Ntt> | 音声入力方法およびこの方法を実施する装置 |
| JPH08339288A (ja) * | 1995-06-14 | 1996-12-24 | Canon Inc | 情報処理装置及びその制御方法 |
| JP2000338994A (ja) * | 1999-05-27 | 2000-12-08 | Fujitsu Ten Ltd | 車載用音声認識装置 |
| JP2004333704A (ja) * | 2003-05-02 | 2004-11-25 | Alpine Electronics Inc | 音声認識装置および方法 |
Family Cites Families (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6553341B1 (en) * | 1999-04-27 | 2003-04-22 | International Business Machines Corporation | Method and apparatus for announcing receipt of an electronic message |
| US6944594B2 (en) * | 2001-05-30 | 2005-09-13 | Bellsouth Intellectual Property Corporation | Multi-context conversational environment system and method |
| US6792408B2 (en) * | 2001-06-12 | 2004-09-14 | Dell Products L.P. | Interactive command recognition enhancement system and method |
| DE10138408A1 (de) * | 2001-08-04 | 2003-02-20 | Philips Corp Intellectual Pty | Verfahren zur Unterstützung des Korrekturlesens eines spracherkannten Textes mit an die Erkennungszuverlässigkeit angepasstem Wiedergabegeschwindigkeitsverlauf |
| US20030046071A1 (en) * | 2001-09-06 | 2003-03-06 | International Business Machines Corporation | Voice recognition apparatus and method |
| JP3686879B2 (ja) * | 2002-05-08 | 2005-08-24 | Necアクセステクニカ株式会社 | ファクシミリ装置 |
| JP4475380B2 (ja) * | 2002-05-15 | 2010-06-09 | パイオニア株式会社 | 音声認識装置及び音声認識プログラム |
| JP4304952B2 (ja) * | 2002-10-07 | 2009-07-29 | 三菱電機株式会社 | 車載制御装置、並びにその操作説明方法をコンピュータに実行させるプログラム |
| US7243068B2 (en) * | 2004-09-10 | 2007-07-10 | Soliloquy Learning, Inc. | Microphone setup and testing in voice recognition software |
| US7724889B2 (en) * | 2004-11-29 | 2010-05-25 | At&T Intellectual Property I, L.P. | System and method for utilizing confidence levels in automated call routing |
| CN1918628A (zh) * | 2004-12-28 | 2007-02-21 | 松下电器产业株式会社 | 声音合成方法和信息提供装置 |
| GB2426368A (en) * | 2005-05-21 | 2006-11-22 | Ibm | Using input signal quality in speeech recognition |
| KR100834679B1 (ko) * | 2006-10-31 | 2008-06-02 | 삼성전자주식회사 | 음성 인식 오류 통보 장치 및 방법 |
| KR20110010939A (ko) * | 2009-07-27 | 2011-02-08 | 삼성전자주식회사 | 휴대용 단말기에서 음성 인식 성능을 향상시키기 위한 장치 및 방법 |
| US20110313762A1 (en) * | 2010-06-20 | 2011-12-22 | International Business Machines Corporation | Speech output with confidence indication |
| US8914290B2 (en) * | 2011-05-20 | 2014-12-16 | Vocollect, Inc. | Systems and methods for dynamically improving user intelligibility of synthesized speech in a work environment |
| US9134952B2 (en) * | 2013-04-03 | 2015-09-15 | Lg Electronics Inc. | Terminal and control method thereof |
| JP2014203207A (ja) * | 2013-04-03 | 2014-10-27 | ソニー株式会社 | 情報処理装置、情報処理方法及びコンピュータプログラム |
| US9965553B2 (en) * | 2013-05-29 | 2018-05-08 | Philip Scott Lyren | User agent with personality |
| US10928976B2 (en) * | 2013-12-31 | 2021-02-23 | Verint Americas Inc. | Virtual assistant acquisitions and training |
| US20180082703A1 (en) * | 2015-04-30 | 2018-03-22 | Longsand Limited | Suitability score based on attribute scores |
| US9558758B1 (en) * | 2015-05-15 | 2017-01-31 | Amazon Technologies, Inc. | User feedback on microphone placement |
| US20160379638A1 (en) * | 2015-06-26 | 2016-12-29 | Amazon Technologies, Inc. | Input speech quality matching |
| US20170076626A1 (en) * | 2015-09-14 | 2017-03-16 | Seashells Education Software, Inc. | System and Method for Dynamic Response to User Interaction |
| KR102815504B1 (ko) * | 2015-09-18 | 2025-05-30 | 삼성전자주식회사 | 콘텐츠 제공 방법 및 이를 수행하는 전자 장치 |
-
2016
- 2016-10-24 CN CN201680079643.7A patent/CN108475507A/zh not_active Withdrawn
- 2016-10-24 WO PCT/JP2016/081470 patent/WO2017130486A1/ja not_active Ceased
- 2016-10-24 EP EP16888071.4A patent/EP3410433A4/en not_active Withdrawn
- 2016-10-24 JP JP2017563687A patent/JPWO2017130486A1/ja active Pending
- 2016-10-24 US US16/069,264 patent/US20190019512A1/en not_active Abandoned
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS62254194A (ja) * | 1986-04-28 | 1987-11-05 | 日本電気株式会社 | 音声認識応答装置 |
| JPS62267800A (ja) * | 1986-05-16 | 1987-11-20 | 株式会社日立製作所 | 音声認識制御方式 |
| JPH02109100A (ja) * | 1988-10-19 | 1990-04-20 | Fujitsu Ltd | 音声入力装置 |
| JPH08335094A (ja) * | 1995-06-08 | 1996-12-17 | Nippon Telegr & Teleph Corp <Ntt> | 音声入力方法およびこの方法を実施する装置 |
| JPH08339288A (ja) * | 1995-06-14 | 1996-12-24 | Canon Inc | 情報処理装置及びその制御方法 |
| JP2000338994A (ja) * | 1999-05-27 | 2000-12-08 | Fujitsu Ten Ltd | 車載用音声認識装置 |
| JP2004333704A (ja) * | 2003-05-02 | 2004-11-25 | Alpine Electronics Inc | 音声認識装置および方法 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP3410433A4 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US12412588B2 (en) | 2017-05-24 | 2025-09-09 | Modulate, Inc. | System and method for creating timbres |
| WO2019058673A1 (ja) * | 2017-09-21 | 2019-03-28 | ソニー株式会社 | 情報処理装置、情報処理端末、情報処理方法、および、プログラム |
| JPWO2019058673A1 (ja) * | 2017-09-21 | 2020-09-10 | ソニー株式会社 | 情報処理装置、情報処理端末、情報処理方法、および、プログラム |
| EP3686881A4 (en) * | 2017-09-21 | 2020-10-07 | Sony Corporation | DEVICE, TERMINAL AND PROCESS FOR PROCESSING INFORMATION, AND ASSOCIATED PROGRAM |
| JP7222354B2 (ja) | 2017-09-21 | 2023-02-15 | ソニーグループ株式会社 | 情報処理装置、情報処理端末、情報処理方法、および、プログラム |
| US11586410B2 (en) | 2017-09-21 | 2023-02-21 | Sony Corporation | Information processing device, information processing terminal, information processing method, and program |
| JP2020507165A (ja) * | 2017-11-21 | 2020-03-05 | ジョンアン インフォメーション テクノロジー サービシズ カンパニー リミテッド | データ可視化のための情報処理方法及び装置 |
| JP2020197973A (ja) * | 2019-06-04 | 2020-12-10 | コニカミノルタ株式会社 | ジョブ処理システム、ジョブ制御装置、音声通知方法、およびコンピュータプログラム |
| JP7408925B2 (ja) | 2019-06-04 | 2024-01-09 | コニカミノルタ株式会社 | ジョブ処理システム、音声通知方法、およびコンピュータプログラム |
| JP2023546989A (ja) * | 2020-10-08 | 2023-11-08 | モジュレイト インク. | コンテンツモデレーションのためのマルチステージ適応型システム |
| JPWO2023286249A1 (ja) * | 2021-07-15 | 2023-01-19 | ||
| JP7605319B2 (ja) | 2021-07-15 | 2024-12-24 | 日本電信電話株式会社 | コミュニケーション支援システム、コミュニケーション支援方法およびプログラム |
| WO2023286249A1 (ja) * | 2021-07-15 | 2023-01-19 | 日本電信電話株式会社 | コミュニケーション支援システム、コミュニケーション支援方法およびプログラム |
| US12341619B2 (en) | 2022-06-01 | 2025-06-24 | Modulate, Inc. | User interface for content moderation of voice chat |
Also Published As
| Publication number | Publication date |
|---|---|
| JPWO2017130486A1 (ja) | 2018-11-22 |
| EP3410433A4 (en) | 2019-01-09 |
| US20190019512A1 (en) | 2019-01-17 |
| CN108475507A (zh) | 2018-08-31 |
| EP3410433A1 (en) | 2018-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017130486A1 (ja) | 情報処理装置、情報処理方法およびプログラム | |
| JP6760271B2 (ja) | 情報処理装置、情報処理方法およびプログラム | |
| US10546582B2 (en) | Information processing device, method of information processing, and program | |
| WO2016151956A1 (ja) | 情報処理システムおよび情報処理方法 | |
| WO2016152200A1 (ja) | 情報処理システムおよび情報処理方法 | |
| WO2018185988A1 (ja) | 情報処理システムおよび記憶媒体 | |
| WO2016136104A1 (ja) | 情報処理装置、情報処理方法及びプログラム | |
| WO2018135057A1 (ja) | 情報処理装置、情報処理方法、及びプログラム | |
| WO2021153101A1 (ja) | 情報処理装置、情報処理方法および情報処理プログラム | |
| WO2016157993A1 (ja) | 情報処理装置、情報処理方法およびプログラム | |
| WO2016088410A1 (ja) | 情報処理装置、情報処理方法およびプログラム | |
| JP2016109726A (ja) | 情報処理装置、情報処理方法およびプログラム | |
| US10798337B2 (en) | Communication device, communication system, and non-transitory computer readable medium storing program | |
| US10643636B2 (en) | Information processing apparatus, information processing method, and program | |
| JP2017211430A (ja) | 情報処理装置および情報処理方法 | |
| JP6798258B2 (ja) | 生成プログラム、生成装置、制御プログラム、制御方法、ロボット装置及び通話システム | |
| WO2018198447A1 (ja) | 情報処理装置および情報処理方法 | |
| JP2016156877A (ja) | 情報処理装置、情報処理方法およびプログラム | |
| JPWO2017187674A1 (ja) | 情報処理装置、情報処理システム、及びプログラム | |
| JP2016180778A (ja) | 情報処理システムおよび情報処理方法 | |
| WO2019082648A1 (ja) | 電子機器、制御装置、制御プログラム及び電子機器の動作方法 | |
| WO2019054009A1 (ja) | 情報処理装置、情報処理方法、およびプログラム | |
| JP2026038196A (ja) | システム | |
| WO2017169499A1 (ja) | 制御装置、制御方法及びコンピュータプログラム |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16888071 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2017563687 Country of ref document: JP Kind code of ref document: A |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2016888071 Country of ref document: EP |
|
| ENP | Entry into the national phase |
Ref document number: 2016888071 Country of ref document: EP Effective date: 20180828 |