WO2017143692A1 - Téléviseur intelligent et son procédé de commande vocale - Google Patents

Téléviseur intelligent et son procédé de commande vocale Download PDF

Info

Publication number
WO2017143692A1
WO2017143692A1 PCT/CN2016/084869 CN2016084869W WO2017143692A1 WO 2017143692 A1 WO2017143692 A1 WO 2017143692A1 CN 2016084869 W CN2016084869 W CN 2016084869W WO 2017143692 A1 WO2017143692 A1 WO 2017143692A1
Authority
WO
WIPO (PCT)
Prior art keywords
voice
smart
user
library
template
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
Application number
PCT/CN2016/084869
Other languages
English (en)
Chinese (zh)
Inventor
汪斯涛
王云华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen TCL Digital Technology Co Ltd
Original Assignee
Shenzhen TCL Digital Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen TCL Digital Technology Co Ltd filed Critical Shenzhen TCL Digital Technology Co Ltd
Publication of WO2017143692A1 publication Critical patent/WO2017143692A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/41—Structure of client; Structure of client peripherals
    • H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/41—Structure of client; Structure of client peripherals
    • H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
    • H04N21/42203—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS] sound input device, e.g. microphone
    • 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
    • G10L15/00—Speech recognition
    • G10L15/28—Constructional details of speech recognition systems
    • G10L15/34—Adaptation of a single recogniser for parallel processing, e.g. by use of multiple processors or cloud computing
    • 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
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/54—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for retrieval

Definitions

  • the present invention relates to the field of voice control technologies, and in particular, to a smart television and a voice control method thereof.
  • the invention provides a smart television and a voice control method thereof, and the main purpose thereof is to solve the technical problem that the voice recognition speed is slow when the voice control smart television is in the prior art.
  • the present invention provides a voice control method for a smart television, and the voice control method of the smart television includes:
  • the voice data storage mode when the voice data input by the user is received, the voice data is parsed to obtain a voice speed of the voice data;
  • the voice control mode when receiving the voice command input by the user, determining the user identifier of the user according to the received voice command;
  • the voice speed of the voice command issued by the user is calculated
  • the smart TV When a voice template matching the voice command exists in the sub-voice library, the smart TV performs a corresponding operation according to a control instruction corresponding to the voice template that matches the voice command.
  • the voice control method of the smart TV further includes the following steps:
  • the voice control method of the smart TV further includes the steps of:
  • the result of the smart TV executing the control instruction is displayed in text form on the display interface of the smart TV.
  • the present invention provides a voice control method for a smart television, and the voice control method of the smart television includes:
  • the voice control mode when receiving the voice command input by the user, determining the user identifier of the user according to the received voice command;
  • the smart TV When a voice template matching the voice command exists in the sub-voice library, the smart TV performs a corresponding operation according to a control instruction corresponding to the voice template that matches the voice command.
  • the voice control method of the smart TV further includes the steps of:
  • the voice data storage mode when the voice data input by the user is received, the voice data is parsed to obtain a voice speed of the voice data;
  • the voice data is stored in a self-speech library corresponding to the voice speed according to the acquired voice speed.
  • determining the user identifier of the user according to the received voice instruction comprises:
  • the voice control method of the smart TV further includes the steps of:
  • the sub-speech library associated with the user identifier is searched from a pre-established standard speech library, and the searched speech template stored in the sub-speech library is matched with the received voice instruction.
  • the steps include:
  • the voice templates stored in the sub-speech library are matched one-to-one with the received voice commands according to the order of use.
  • the voice control method of the smart TV further includes the following steps:
  • the voice control method of the smart TV further includes the steps of:
  • the result of the smart TV executing the control instruction is displayed in text form on the display interface of the smart TV.
  • the present invention also provides a smart television, the smart television comprising:
  • An identifier determining module configured to determine, according to the received voice instruction, a user identifier of the user when receiving a voice instruction input by a user in a voice control mode
  • a voice matching module configured to search a sub-speech library associated with the user identifier from a pre-established standard voice library, and perform the searched voice template stored in the sub-voice library with the received voice command match;
  • an instruction execution module configured to: when a voice template matching the voice instruction exists in the child voice library, control a smart TV to perform a corresponding operation according to a control instruction corresponding to the voice template that matches the voice instruction.
  • the smart TV further includes:
  • a speech rate obtaining module configured to parse the voice data when the voice data input by the user is received in the voice data storage mode, to obtain a voice speed of the voice data
  • a data storage module configured to store the voice data into a self-speech library corresponding to the voice speed according to the acquired voice speed.
  • the identifier determining module comprises:
  • a speech rate calculation unit configured to calculate a voice speed of the voice command sent by the user when receiving a voice instruction input by the user in the voice control mode
  • an identifier obtaining unit configured to determine a voice speed interval corresponding to the voice speed, and acquire a user identifier corresponding to the voice speed interval.
  • the smart TV further includes:
  • the number update module is configured to update the number of uses of the voice template that matches the voice instruction, and store the updated usage count in association with the voice template.
  • the voice matching module includes:
  • a template sorting unit configured to search a sub-speech library associated with the user identifier from a pre-established standard speech library, and sort the voice templates in the sub-speech library according to usage times at least;
  • the voice matching unit is configured to match the voice template stored in the sub-voice library with the received voice command one by one according to the order of use.
  • the smart TV further includes:
  • a display module configured to display text information corresponding to the voice template matched with the voice instruction on a display interface of the smart TV; and display the smart TV to execute the control instruction in a text form on a display interface of the smart television After the result.
  • the smart television and the voice control method thereof when receiving a voice instruction input by a user, determine a user identifier of the user according to the received voice command, and search for a child associated with the user identifier from a pre-established standard voice library.
  • the voice library matches the voice template stored in the found sub-speech library with the received voice command, and when the voice template matches the voice command in the child voice library, the voice template corresponding to the voice command is controlled.
  • the instruction controls the smart TV to perform a corresponding operation, and the present invention pre-establishes a sub-speech library for each user using the smart TV, and associates with the user identifier of the user, and when the voice template in the voice library is matched with the voice instruction, After determining the user corresponding to the received voice command, the user identifier of the user is obtained, and the voice matching can be directly performed in the sub-speech library associated with the user identifier, thereby reducing the calculation amount of the voice matching, and eliminating the need to go to the cloud.
  • the comparison of the speech library greatly improves the speed of speech recognition and accelerates The response speed of the voice instruction.
  • FIG. 1 is a flowchart of a first embodiment of a voice control method for a smart television according to the present invention
  • FIG. 2 is a schematic flowchart of a step of acquiring a user identifier in a first embodiment of a voice control method for a smart television according to the present invention
  • FIG. 3 is a flowchart of a second embodiment of a voice control method for a smart television according to the present invention.
  • FIG. 4 is a schematic flowchart of a step of matching a voice command in a second embodiment of a voice control method for a smart television according to the present invention
  • FIG. 5 is a schematic diagram of functional modules of a first embodiment of a smart television according to the present invention.
  • FIG. 6 is a schematic diagram of a refinement function module of an identifier acquisition module in a first embodiment of a smart television according to the present invention
  • FIG. 7 is a schematic diagram of functional modules of a second embodiment of a smart television according to the present invention.
  • FIG. 8 is a schematic diagram of a refinement function module of a voice matching module in a second embodiment of a smart television according to the present invention.
  • the invention provides a voice control method for a smart TV.
  • FIG. 1 a flow chart of a first embodiment of a voice control method for a smart television according to the present invention is shown.
  • the voice control method of the smart television includes:
  • Step S10 In the voice control mode, when receiving the voice instruction input by the user, determining the user identifier of the user according to the received voice command;
  • Step S20 Searching a sub-speech library associated with the user identifier from a pre-established standard speech library, and matching the searched speech template stored in the sub-speech library with the received voice command;
  • the control for triggering the voice control mode is set on the remote control device of the smart TV or directly on the smart TV.
  • the voice control mode can also be triggered by the mobile terminal.
  • the voice command sent by the user may be collected by the remote control device or the mobile terminal, and sent to the smart TV through wireless communication.
  • the voice command sent by the user can also be directly collected through the microphone of the smart TV.
  • the user identifier of the user is determined according to the voice command.
  • the voice characteristics of each user are not the same. For example, it is possible to determine which user is performing voice control according to the tone, voice speed, and the like.
  • step S10 may include the following refinement steps:
  • Step S11 when receiving a voice instruction input by the user in the voice control mode, calculating a voice speed at which the user sends the voice command;
  • Step S12 Determine a voice speed interval corresponding to the voice speed, and obtain a user identifier corresponding to the voice speed interval.
  • the corresponding user is determined by the voice speed, and the user stores his voice as a voice template on the smart TV in advance, and the smart TV analyzes the voice template of the user to determine the voice speed of the user, and pre-divides the voice speed interval.
  • the unit speaks 1.5-2 characters for fast speech in 1 second, and 1-1.5 characters for medium-speed speech in 1 second, and 0.5-1 characters for low-speed speech in 1 second; judges the speech speed to which the speech speed belongs.
  • the voice speed interval is associated with the user identifier of the user, and at the same time, a standard voice library is established, the standard voice library is divided into multiple sub-speech libraries, and each user is assigned a sub-speech library and the user identifier of the user.
  • the user can update the voice template in the sub-voice library corresponding to the user ID at any time, for example, modify, add or delete, etc. .
  • the voice speed of the voice command issued by the user is calculated, wherein the voice speed is calculated in many ways, for example, Converting the voice command input by the user into text, and obtaining the duration of the voice command, thereby obtaining the number of characters sent by the user per second as the voice speed; or performing waveform analysis on the received voice signal to obtain the voice speed of the user If the received signal is a digital signal, the digital signal is converted into an analog signal, and then waveform analysis is performed to obtain the user's voice speed.
  • the sub-speech library associated with the user identifier is searched from the pre-established standard voice library, and the voice template stored in the found sub-speech library is matched with the received voice command.
  • Step S30 When there is a voice template matching the voice command in the sub-voice library, control the smart TV to perform a corresponding operation according to a control instruction corresponding to the voice template matched by the voice command.
  • the smart TV When the voice template matching the voice command sent by the user is found in the sub-voice library corresponding to the user identifier, the smart TV performs the corresponding operation according to the control instruction corresponding to the voice template.
  • step S20 the voice control method of the smart television further includes the steps of:
  • the voice control method of the smart television further includes the following steps:
  • the result of the smart TV executing the control instruction is displayed in text form on the display interface of the smart TV.
  • the result of the smart TV executing the control command may also be fed back in a voice form.
  • the voice control method of the smart TV when receiving the voice instruction input by the user, determines the user identifier of the user according to the received voice command, and searches for the child associated with the user identifier from the pre-established standard voice library.
  • the voice library matches the voice template stored in the found sub-speech library with the received voice command, and when the voice template matches the voice command in the child voice library, the voice template corresponding to the voice command is controlled.
  • the instruction controls the smart TV to perform a corresponding operation, and the present invention pre-establishes a sub-speech library for each user using the smart TV, and associates with the user identifier of the user, and when the voice template in the voice library is matched with the voice instruction, After determining the user corresponding to the received voice command, the user identifier of the user is obtained, and the voice matching can be directly performed in the sub-speech library associated with the user identifier, thereby reducing the calculation amount of the voice matching, and eliminating the need to go to the cloud.
  • the comparison of the speech library greatly improves the speed of speech recognition and accelerates The response speed of the voice instruction.
  • a second embodiment of a voice control method for a smart television of the present invention is proposed based on a first embodiment of a voice control method for a smart television of the present invention.
  • the method is different from the first embodiment in that the voice control method of the smart TV further includes:
  • Step S40 in the voice data storage mode, when the voice data input by the user is received, parsing the voice data to obtain a voice speed of the voice data;
  • Step S50 storing the voice data into a self-speech library corresponding to the voice speed according to the acquired voice speed.
  • the user can record his own voice as a voice template and store it in the local storage space of the smart TV.
  • the smart TV can directly perform local voice recognition, without comparing to the voice library in the cloud, and improving the speed of voice recognition, further Users can also upload voices from the local voice library to the cloud as a backup.
  • the user controls the smart TV to enter the voice data storage mode, and when receiving the voice data input by the user, according to the voice speed of the voice data, that is, the user's speech rate is allocated, then the current user's speech rate is medium.
  • the user's voice data is automatically stored in the self-speech library corresponding to the voice speed.
  • voice data the user is distinguished according to the identity of the mobile terminal.
  • the sub-speech library can also be created as follows:
  • the sub-speech library is established, and the established sub-speech library is associated with the user identifier input by the user; when the voice data input by the user is received, the received voice data is stored to the established office.
  • the sub-speech library associated with the user identifier is used as a speech template.
  • Setting the voice data storage mode when setting the voice template, entering the voice data storage mode, establishing a sub-voice library, associating the established sub-voice library with the user identifier input by the user, and receiving the voice data input by the user,
  • the received voice data is stored in the sub-speech library associated with the established user identity as a voice template.
  • the voice control method of the smart TV provides a sub-speech library for each user using the smart TV, and is associated with the user identifier of the user, and when the voice template in the voice library is matched with the voice command, According to the voice speed of the user, the corresponding voice data can be allocated to the corresponding sub-speech library, which greatly improves the speed of voice recognition, thereby speeding up the response speed of the voice command.
  • a third embodiment of the voice control method of the smart television of the present invention is proposed based on the first embodiment of the voice control method of the smart television of the present invention.
  • the method is different from the first embodiment in that after the step S40, the method further comprises the following steps:
  • step S20 may include the following refinement steps:
  • Step S21 Searching a sub-speech library associated with the user identifier from a pre-established standard speech library, and sorting the speech templates in the sub-speech library according to the number of uses;
  • Step S22 Match the voice template stored in the sub-speech library with the received voice command one by one according to the order of use.
  • the used voice template is updated by the number of uses.
  • the initial usage times are zero. Each time the match is successfully matched, the number is increased by 1. In this way, the number of times the user uses each voice template is counted.
  • the voice templates in the child voice library are sorted according to the number of uses. Then, the voice template stored in the sub-speech library is matched with the received voice command one by one according to the order of use.
  • the voice control method of the smart TV is based on the update of the usage number of the voice template and the associated storage, and when the voice template stored in the child voice library is matched with the received voice command, The number of times is matched one by one in at least one order, so that some frequently used voice commands can match the corresponding voice template more quickly, further improving the speed of voice recognition, thereby speeding up the response speed of voice commands.
  • the invention also proposes a smart television.
  • FIG. 5 it is a schematic diagram of functional modules of a first embodiment of a smart television of the present invention.
  • the smart television includes an identification determination module 10, a voice matching module 20, and an instruction execution module 30.
  • the identifier determining module 10 is configured to determine, according to the received voice instruction, the user identifier of the user when receiving the voice instruction input by the user in the voice control mode;
  • the voice matching module 20 is configured to search a sub-speech library associated with the user identifier from a pre-established standard voice library, and search the found voice template stored in the sub-speech library with the received voice command. Matching;
  • the control for triggering the voice control mode is set on the remote control device of the smart TV or directly on the smart TV.
  • the voice control mode can also be triggered by the mobile terminal.
  • the voice command sent by the user may be collected by the remote control device or the mobile terminal, and sent to the smart TV through wireless communication.
  • the voice command sent by the user can also be directly collected through the microphone of the smart TV.
  • the identifier determining module 10 receives the voice instruction input by the user, the identifier of the user is determined according to the voice command.
  • the voice characteristics of each user are not the same. For example, it is possible to determine which user is performing voice control according to the tone, voice speed, and the like.
  • the identification determining module 10 may include the following refinement unit:
  • the speech rate calculation unit 11 is configured to calculate a speech speed of the voice instruction sent by the user when receiving a voice instruction input by the user in the voice control mode;
  • the identifier obtaining unit 12 is configured to determine a voice speed interval corresponding to the voice speed, and acquire a user identifier corresponding to the voice speed interval.
  • the corresponding user is determined by the voice speed.
  • the user stores his voice as a voice template on the smart TV in advance, analyzes the voice template of the user, determines the voice speed of the user, and pre-divides the voice speed interval, for example,
  • the unit speaks 1.5-2 characters for fast speech in 1 second, and 1-1.5 characters for medium-speed speech in 1 second, and 0.5-1 characters for low-speed speech in 1 second; judges the speech speed interval to which the speech velocity belongs.
  • the voice speed interval is associated with the user identifier of the user, and a standard voice library is established, the standard voice library is divided into multiple sub-voice libraries, and each user is assigned a sub-speech library and associated with the user identifier of the user.
  • the foregoing voice template recorded by the user in advance is stored in the sub-voice library corresponding to the user identifier, and corresponding control commands are set for each voice template, such as channel addition, channel reduction, weather inquiry, application opening instruction, volume adjustment instruction, and the like. Etc., the user can set it according to his own needs. When inputting voice commands, only input and voice are required. Voice content to the same board.
  • the user can update the voice template in the sub-voice library corresponding to the user ID at any time, for example, modify, add or delete, etc. .
  • the speech rate calculation unit 11 calculates the voice speed of the voice command issued by the user according to the received voice command, wherein the voice speed is calculated in a plurality of manners.
  • the voice command input by the user may be converted into text, and the duration of the voice command may be acquired, thereby obtaining the number of characters sent by the user per second as the voice speed; or waveform analysis of the received voice signal may be performed.
  • the received signal is a digital signal, convert the digital signal into an analog signal and perform waveform analysis to obtain the user's voice speed.
  • the voice matching module 20 searches the pre-established standard voice library for the sub-speech library associated with the user identifier, and matches the voice template stored in the found sub-speech library with the received voice command.
  • the instruction execution module 30 is configured to, when a voice template matching the voice instruction exists in the child voice library, control a smart TV to perform a corresponding operation according to a control instruction corresponding to the voice template matched by the voice instruction.
  • the instruction execution module 30 controls the smart TV to perform the corresponding operation according to the control instruction corresponding to the voice template.
  • the smart TV further includes:
  • a display module configured to display text information corresponding to the voice template matched with the voice instruction on a display interface of the smart TV; and display the smart TV to execute the control instruction in a text form on a display interface of the smart television After the result.
  • the smart TV can also feed back the result of the smart TV executing the control command in a voice form.
  • the smart TV when receiving the voice instruction input by the user, determines the user identifier of the user according to the received voice command, and searches for a sub-voice library associated with the user identifier from a pre-established standard voice library, and Matching the voice template stored in the found sub-speech library with the received voice command.
  • the voice template matches the voice command in the sub-voice library
  • the smart TV is controlled according to the control command corresponding to the voice template matched with the voice command.
  • the present invention pre-establishes a sub-speech library for each user using the smart TV, and associates with the user identifier of the user, and only needs to determine when the speech template in the speech library is matched with the voice instruction.
  • the user identifier of the user is obtained, and the voice matching is directly performed in the sub-speech library associated with the user identifier, which reduces the calculation amount of the voice matching, and does not need to go to the cloud voice library. Contrast, greatly improving the speed of speech recognition, which in turn speeds up the voice command Speed.
  • a second embodiment of the smart television of the present invention is presented based on the first embodiment of the smart television of the present invention.
  • the method is different from the first embodiment in that the smart TV further includes the following modules:
  • the speech rate obtaining module 40 is configured to parse the voice data when the voice data input by the user is received in the voice data storage mode, and obtain the voice speed of the voice data;
  • the data storage module 50 is configured to store the voice data into a self-speech library corresponding to the voice speed according to the acquired voice speed.
  • the user can record his own voice as a voice template and store it in the local storage space of the smart TV.
  • the smart TV can directly perform local voice recognition, without comparing to the voice library in the cloud, and improving the speed of voice recognition, further Users can also upload voices from the local voice library to the cloud as a backup.
  • the user controls the smart TV to enter the voice data storage mode.
  • the data storage module 50 allocates according to the voice speed of the voice data, that is, the user's speech rate, then, the current user's When the speech rate is medium speed, the data storage module 50 will automatically store the user's voice data into the self-speech library corresponding to the voice speed.
  • it is also possible to identify which user is the user and store the voice data in the corresponding self-speech library for example, by different timbre, or when the user sends the mobile terminal through a mobile phone or the like.
  • voice data the user is distinguished according to the identity of the mobile terminal.
  • the digital television may further include:
  • a voice library establishing module the voice is in the voice data storage mode, the child voice library is established, and the established child voice library is associated with the user identifier input by the user; the data storage module 50 is further configured to receive the voice data input by the user.
  • the received voice data is stored in the sub-speech library associated with the established user identity as a voice template.
  • the voice data storage mode is set, and when the voice template is set, the voice data storage mode is entered, the voice library establishment module establishes a sub-voice library, and the established sub-voice library is associated with the user identifier input by the user, and the data storage module 50 Receiving voice data input by the user, and storing the received voice data into the sub-speech library associated with the established user identifier as a voice template.
  • the smart TV provided in this embodiment establishes a sub-speech library for each user who uses the smart TV, and associates with the user identifier of the user, and when the voice template in the voice library is matched with the voice instruction, the user can be
  • the voice speed can be allocated to the corresponding sub-speech database, which greatly improves the speed of speech recognition, thereby speeding up the response speed of the voice command.
  • a third embodiment of the smart television of the present invention is proposed based on the first embodiment of the smart television of the present invention.
  • the method is different from the first embodiment in that the smart TV further includes the following modules:
  • the number update module is configured to update the number of uses of the voice template that matches the voice instruction, and store the updated usage count in association with the voice template.
  • the voice matching module 20 may include the following refinement unit on the basis that the number update module performs the update of the usage number of the voice template and associates the storage:
  • the template sorting unit 21 is configured to search for a sub-speech library associated with the user identifier from a pre-established standard speech library, and sort the speech templates in the sub-speech library according to the number of uses;
  • the voice matching unit 22 is configured to match the voice template stored in the sub-voice library with the received voice command one by one according to the order of use.
  • the used voice template is updated by the number of uses.
  • the initial usage times are zero. Each time the match is successfully matched, the number is increased by 1. In this way, the number of times the user uses each voice template is counted.
  • the template sorting unit 21 uses the voice template in the child voice library according to the number of times of use. At least the sorting is performed, and then the voice matching unit 22 matches the voice template stored in the sub-speech library with the received voice command one by one according to the order of use.
  • the number of times of use is at least The order is matched one by one, so that some frequently used voice commands can match the corresponding voice template more quickly, further improving the speed of voice recognition, thereby speeding up the response speed of voice commands.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Theoretical Computer Science (AREA)
  • Selective Calling Equipment (AREA)
  • User Interface Of Digital Computer (AREA)
  • Television Systems (AREA)

Abstract

L'invention concerne un procédé de commande vocale pour un téléviseur intelligent, les processus du procédé comprenant : dans un mode de commande vocale, la détermination, lors de la réception d'une instruction vocale saisie par un utilisateur, de l'identifiant d'utilisateur de l'utilisateur conformément à l'instruction vocale reçue (S10) ; la recherche d'une sous-base de données de parole associée à l'identifiant d'utilisateur dans une base de données de parole standard préétablie, et la comparaison d'un modèle de parole stocké dans la sous-base de données de parole précédemment trouvée à l'instruction vocale reçue (S20) ; lorsqu'un modèle de parole qui correspond à l'instruction vocale est présent dans la sous-base de données de parole, la commande du téléviseur intelligent, conformément à une instruction de commande correspondant au modèle de parole qui correspond à l'instruction vocale, pour exécuter l'opération correspondante (S30). Ledit téléviseur intelligent résout le problème technique de faible vitesse de reconnaissance vocale quand le téléviseur est sous commande vocale.
PCT/CN2016/084869 2016-02-26 2016-06-04 Téléviseur intelligent et son procédé de commande vocale Ceased WO2017143692A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610109679.7 2016-02-26
CN201610109679.7A CN105791931A (zh) 2016-02-26 2016-02-26 智能电视及其语音控制方法

Publications (1)

Publication Number Publication Date
WO2017143692A1 true WO2017143692A1 (fr) 2017-08-31

Family

ID=56402906

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/084869 Ceased WO2017143692A1 (fr) 2016-02-26 2016-06-04 Téléviseur intelligent et son procédé de commande vocale

Country Status (2)

Country Link
CN (1) CN105791931A (fr)
WO (1) WO2017143692A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108419109A (zh) * 2018-03-06 2018-08-17 杭州政信金服互联网科技有限公司 一种会议直播声音调节方法和系统
CN108829001A (zh) * 2018-06-25 2018-11-16 广东好太太科技集团股份有限公司 一种晾衣机的语音控制方法及晾衣机

Families Citing this family (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018027843A1 (fr) * 2016-08-11 2018-02-15 张焰焰 Procédé d'acquisition de données et ensemble de télévision de technologie d'entrée d'instruction de télévision
CN106384592A (zh) * 2016-11-22 2017-02-08 浙江圣奥家具制造有限公司 一种智能语音控制的桌子及其控制方法
CN108172221A (zh) * 2016-12-07 2018-06-15 广州亿航智能技术有限公司 基于智能终端的操控飞行器的方法和装置
CN106778927A (zh) * 2016-12-30 2017-05-31 深圳Tcl新技术有限公司 更新电视语义识别词库方法及装置
CN108319829B (zh) * 2017-01-11 2022-05-06 中兴通讯股份有限公司 一种声纹验证方法和装置
CN106997763A (zh) * 2017-03-17 2017-08-01 浙江大学 一种基于语音信号频域处理的空调控制装置
CN109089140A (zh) * 2017-06-14 2018-12-25 北京优朋普乐科技有限公司 一种语音控制方法及装置
CN110020219B (zh) * 2017-11-09 2026-01-16 北京京东尚科信息技术有限公司 用于服务器的信息处理方法和装置
CN110570846B (zh) * 2018-06-05 2022-04-22 青岛海信移动通信技术股份有限公司 一种语音控制方法、装置及手机
CN108932942A (zh) * 2018-06-26 2018-12-04 四川斐讯信息技术有限公司 一种实现智能音箱人机对话的系统及其方法
CN109119076B (zh) * 2018-08-02 2022-09-30 重庆柚瓣家科技有限公司 一种老人用户交流习惯的收集系统及方法
CN109036424A (zh) * 2018-08-30 2018-12-18 出门问问信息科技有限公司 语音识别方法、装置、电子设备及计算机可读存储介质
CN109065056B (zh) * 2018-09-26 2021-05-11 珠海格力电器股份有限公司 一种语音控制空调的方法及装置
CN111192573B (zh) * 2018-10-29 2023-08-18 宁波方太厨具有限公司 基于语音识别的设备智能化控制方法
CN111105798B (zh) * 2018-10-29 2023-08-18 宁波方太厨具有限公司 基于语音识别的设备控制方法
CN109741738A (zh) * 2018-12-10 2019-05-10 平安科技（深圳）有限公司 语音控制方法、装置、计算机设备及存储介质
CN111312253A (zh) * 2018-12-11 2020-06-19 青岛海尔洗衣机有限公司 语音控制方法、云端服务器及终端设备
CN110136700B (zh) * 2019-03-15 2021-04-20 湖北亿咖通科技有限公司 一种语音信息处理方法及装置
CN110010131B (zh) * 2019-04-04 2022-01-04 深圳市语芯维电子有限公司 一种语音信息处理的方法和装置
CN110459222A (zh) * 2019-09-06 2019-11-15 Oppo广东移动通信有限公司 语音控制方法、语音控制装置及终端设备
CN111081248A (zh) * 2019-12-27 2020-04-28 安徽仁昊智能科技有限公司 一种人工智能语音识别装置
CN112017653A (zh) * 2020-07-13 2020-12-01 武汉戴美激光科技有限公司 具有语音识别功能的激光治疗手柄及调节方法
CN111916084A (zh) * 2020-09-09 2020-11-10 深圳创维－Rgb电子有限公司 智能家居语音控制方法及装置、设备、存储介质
CN112516584B (zh) * 2020-12-21 2024-06-04 上海连尚网络科技有限公司 游戏角色的控制方法和装置
CN112885354B (zh) * 2021-01-25 2022-09-23 海信视像科技股份有限公司 一种显示设备、服务器及基于语音的显示控制方法
CN113593554A (zh) * 2021-07-21 2021-11-02 深圳市芯中芯科技有限公司 一种语音识别离线命令词唤醒应用方法与系统
CN113948082A (zh) * 2021-10-13 2022-01-18 阿波罗智联(北京)科技有限公司 车辆的控制方法、用于车辆的控制的映射关系生成方法
CN121191512A (zh) * 2025-10-13 2025-12-23 宁波友好智能安防科技有限公司 基于语音识别的智能床头柜语音控制方法

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040015356A1 (en) * 2002-07-17 2004-01-22 Matsushita Electric Industrial Co., Ltd. Voice recognition apparatus
CN101478648A (zh) * 2008-10-17 2009-07-08 康佳集团股份有限公司 一种电视机语音控制方法
CN101894553A (zh) * 2010-07-23 2010-11-24 四川长虹电器股份有限公司 电视机语音控制的实现方法
US20120176313A1 (en) * 2011-01-06 2012-07-12 Samsung Electronics Co., Ltd. Display apparatus and voice control method thereof
CN102708858A (zh) * 2012-06-27 2012-10-03 厦门思德电子科技有限公司 基于编组方式的语音库实现语音识别系统及其方法
CN102750126A (zh) * 2012-06-27 2012-10-24 深圳Tcl新技术有限公司 语音输入方法及终端
CN104778946A (zh) * 2014-01-10 2015-07-15 中国电信股份有限公司 语音控制方法和系统

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5695447B2 (ja) * 2011-03-01 2015-04-08 株式会社東芝 テレビジョン装置及び遠隔操作装置
CN103903621A (zh) * 2012-12-26 2014-07-02 联想(北京)有限公司 一种语音识别的方法及电子设备
CN103456303A (zh) * 2013-08-08 2013-12-18 四川长虹电器股份有限公司 一种语音控制的方法和智能空调系统

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040015356A1 (en) * 2002-07-17 2004-01-22 Matsushita Electric Industrial Co., Ltd. Voice recognition apparatus
CN101478648A (zh) * 2008-10-17 2009-07-08 康佳集团股份有限公司 一种电视机语音控制方法
CN101894553A (zh) * 2010-07-23 2010-11-24 四川长虹电器股份有限公司 电视机语音控制的实现方法
US20120176313A1 (en) * 2011-01-06 2012-07-12 Samsung Electronics Co., Ltd. Display apparatus and voice control method thereof
CN102708858A (zh) * 2012-06-27 2012-10-03 厦门思德电子科技有限公司 基于编组方式的语音库实现语音识别系统及其方法
CN102750126A (zh) * 2012-06-27 2012-10-24 深圳Tcl新技术有限公司 语音输入方法及终端
CN104778946A (zh) * 2014-01-10 2015-07-15 中国电信股份有限公司 语音控制方法和系统

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108419109A (zh) * 2018-03-06 2018-08-17 杭州政信金服互联网科技有限公司 一种会议直播声音调节方法和系统
CN108829001A (zh) * 2018-06-25 2018-11-16 广东好太太科技集团股份有限公司 一种晾衣机的语音控制方法及晾衣机

Also Published As

Publication number Publication date
CN105791931A (zh) 2016-07-20

Similar Documents

Publication Publication Date Title
WO2017143692A1 (fr) Téléviseur intelligent et son procédé de commande vocale
WO2018043991A1 (fr) Procédé et appareil de reconnaissance vocale basée sur la reconnaissance de locuteur
WO2014107097A1 (fr) Appareil d'affichage et procédé de commande dudit appareil d'affichage
WO2018006489A1 (fr) Procédé et dispositif d'interaction vocale de terminal
WO2017160073A1 (fr) Procédé et dispositif pour une lecture, une transmission et un stockage accélérés de fichiers multimédia
WO2014107101A1 (fr) Appareil d'affichage et son procédé de commande
WO2017156893A1 (fr) Procédé de commande vocale et téléviseur intelligent
WO2019051902A1 (fr) Procédé de commande de terminal, climatiseur et support d'informations lisible par un ordinateur
WO2016032021A1 (fr) Appareil et procédé de reconnaissance de commandes vocales
WO2019061613A1 (fr) Procédé de criblage d'habilitation pour un prêt, dispositif et support de stockage lisible par ordinateur
WO2017054488A1 (fr) Procédé de commande de lecture de télévision, serveur et système de commande de lecture de télévision
WO2017054592A1 (fr) Terminal et procédé d'affichage d'interface
WO2013127233A1 (fr) Procédé de déverrouillage de touche basée sur un téléphone cellulaire et téléphone cellulaire
WO2018032680A1 (fr) Procédé et système de lecture audio et vidéo
WO2013170662A1 (fr) Procédé et dispositif d'ajout d'informations d'amis, et support de stockage informatique
WO2017005066A1 (fr) Procédé et appareil d'enregistrement d'estampille temporelle de synchronisation audio et vidéo
WO2017045441A1 (fr) Procédé et appareil de lecture audio utilisant une télévision intelligente
WO2019085543A1 (fr) Système de télévision et procédé de commande de télévision
WO2016127458A1 (fr) Procédé de calcul de similitude de mots amélioré et dispositif basé sur un dictionnaire sémantique
WO2018097504A2 (fr) Dispositif électronique et procédé de mise à jour de carte de canaux associée
WO2018233221A1 (fr) Procédé de sortie sonore multi-fenêtre, télévision et support de stockage lisible par ordinateur
WO2018188196A1 (fr) Procédé de commande de version de données, contrôleur de version de données, dispositif et support de stockage lisible par ordinateur
WO2018188342A1 (fr) Procédé, appareil et dispositif permettant de générer un fichier de script, et support d'informations lisible par ordinateur
WO2019114127A1 (fr) Procédé et dispositif de sortie vocale pour conditionneur d'air
WO2017080195A1 (fr) Procédé et dispositif de reconnaissance audio

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16891146

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 11/01/2019)

122 Ep: pct application non-entry in european phase

Ref document number: 16891146

Country of ref document: EP

Kind code of ref document: A1