JPH01293428A - Sentence preparing system - Google Patents

Abstract

PURPOSE:To confirm a sentence displayed at a picture while a voice is heard by using a silence section detecting signal sound-recorded to a sound recording sentence and delimiter stored in the memory as a timing signal to obtain the synchronization and operating the reproducing and displaying of a sound recording/reproducing device while the synchronization is mutually obtained. CONSTITUTION:When a silence section to display the break of the recognition unit is detected from a sentence sound recorded to a sound recorder 2, a silence section detecting signal to show that the silence section is detected is sound recorded at the silence section and the voice recognized result is stored into a memory 8 by sticking a delimiter for a recognition unit. Such silence section detecting signal and the delimiter are used, the synchronization of the sentence read and displayed from the memory 8 and the voice of the sound recording/ reproducing device 2 is obtained, and by following the sentence displayed on the screen, the sound recording voice of a sound recording/reproducing device 2 is reproduced. Thus, the dislocation of the sound recording part and the displaying part can be eliminated and while the sound recording voice is heard, the sentence of the recognition result can be confirmed.

Description

DETAILED DESCRIPTION OF THE INVENTION (a) Field of Industrial Application The present invention relates to a system for creating sentences by voice recognition.

(b) Conventional technology A text creation system that performs speech recognition and converts it into text by recording speech on a recording/playback device such as a tape recorder, and inputting the output playback speech into a speech recognition device. is being developed (Japanese Unexamined Patent Publication No. 58-15
No. 8736).

Conventionally, in a device that combines a recording/playback device and voice recognition, the text played back by the recording/playback device and the part that displays data read from a storage device on a display device operate independently. In other words, the R sound playback device was only used to input audio to the recognition device, and the display device only displayed the data read from the storage device, so the display screen could be used while listening to the recorded audio. It was not possible to check the text displayed on the screen.

(c) Problems to be Solved by the Invention The present invention has been made in view of the above-mentioned points, and provides a text creation system that allows text confirmation of recognition results while listening to recorded audio.

(d) Means for Solving the Problems When the sentence creation nostem of the present invention detects a silent interval representing a division of recognition units from a sentence recorded on a recording device, it detects the silent interval and does not stop running. Recording a silent section detection signal in the silent section, storing the voice recognition result in a storage device with a delimiter attached to each recognition unit, and using the silent section detection signal and the delimiter,
By synchronizing the text read from the storage device and displayed with the audio from the recording/playback device, the recorded audio from the recording/playback device is played back following the text displayed on the screen. .

(E) Effect According to the present invention, the silent section detection signal recorded in the recorded text and the delimiter recorded on the display side are used as timing signals for synchronization, and the recording/playback device and the display are synchronized. Since these are controlled so that they operate in synchronization with each other, it is possible to eliminate any discrepancies between the recorded portion and the displayed portion.

(f) Embodiment FIG. 1 shows an external view of a desk cheating machine which adopts the present invention and creates sentences by sweat voice input.
shows a functional block diagram of the machine.

In Fig. 2, (1) is a speech recognition section equipped with a circuit inside the main body of Fig. 1 (<100), and its details are shown in the block diagram of Fig. 3. ! Preprocessing ff1(11) [aS 4 figure], iJ[[
Sound pressure from 1lI (11)! A feature extraction unit (1) that extracts parameters indicating acoustic features from the input audio signal.
2) [Fig. 5], a word recognition unit (13) that performs word recognition of input speech based on the feature parameters obtained from the extraction unit (12) [Fig. ], and a candidate creation unit (15) that creates candidates for a recognized @word character string or a recognized syllable character based on the recognition results from any of these recognition units (13) and (14).

Furthermore, in Figure 2, 2) is the main body (1) as shown in Figure 1.
Cheap Lay 1 that can be mechanically and electrically detached from 00)
(3) is a headphone type microphone as shown in FIG. This is an input switching unit [FIG. 8] that performs connection switching. (6) is a display device for displaying character strings etc. generated based on the recognition results; (7) is a keyboard for inputting various control signals of the dayc-cheating machine; (8) is a keyboard for inputting various control signals of the dayc-cheating machine. (9) A storage device such as a magnetic disk device that stores the character string generated by
is a speaker (10
) is a speech synthesis unit that reads out aloud.

Note that (5) is a control section consisting of a microprocessor, which controls the operations of the above-mentioned sections.

There are two ways to create sentences using the desk cheating machine configured as described above, and each will be explained in detail below.

The first method is to collect the main voice from the microphone (3) using the voice recognition unit (
1), performs voice recognition, converts the input voice into a character string, displays it on the display device (6), and at the same time inputs it into the storage device (8).
).

The second method is to record the text you want to input in advance using a recording and playback device (2
) and use this recording/playback device 1! (2) By connecting ° to this device and inputting the recorded text to the speech recognition unit (1), it performs speech recognition, converts the human voice into a character string, and displays it on the display device (6). , and storage device (8) at the same time
Store the results in .

As mentioned above, there are two ways to input audio.C1
6. Switching of inputs is performed in the input switching section (4). i! In addition to switching the input, the input switching section (4) also switches whether the recording/playback device (2) records the recording signal (2) or the audio input from the microphone (3). .

The operations from voice recording to text creation will be explained in detail below.

(1) Voice Registration Process Before performing voice recognition, voice registration is performed in order to create a standard pattern of voice necessary for voice recognition.

First, the syllable registration mode will be described.

The standard pattern described here is the speech recognition unit (1)
It serves as a reference pattern during pattern matching in the phrase recognition section (14) of the phrase recognition section (14), and specifically, it is the syllable standard pattern memory (14d) of the phrase recognition section (14) as shown in Fig. 7.
).

The method of registering voice in this digital cheating machine is to first operate the switch (14sl) shown in Fig.
There are three ways to connect these.

The first method is to attach a microphone (3) to the main body (100) of the machine.
A method of directly inputting registered speech, analyzing this registered speech with the speech recognition unit (1), creating a standard pattern, and storing the created standard pattern in the syllable standard pattern memory (14d) and storage device 8). It is.

The second method is to input the registered voice by connecting the recording and playback device (2) on which the registered voice has been recorded in advance to the main body (100) and playing back the recorded registered voice. In this method, registered speech is analyzed by a speech recognition unit (1), a standard Bakun is created, and the created standard pattern is stored in a syllable standard pattern memory (14d) and a storage device (8).

The third method is to connect the microphone (3) to the main body (100) of this machine.
At this time, the recording/playback device (2) is connected to the main unit (100), and while recording the input audio to the recording/playback device (2), the registered audio is input directly from the main unit (100) side. Now, analyze the registered voice from the microphone (3), create a standard pattern, store the created standard pattern in the storage device (8), and then finish inputting the voice to this microphone (3). Then, following this, the recorded voice is played back on the recording and playback device (2), this recorded registered voice is analyzed by the voice recognition unit (1), a standard pattern is created, and the created standard pattern is converted into syllables. This is a method of storing the standard pattern memory (14d) and at the same time storing it in the storage device (8) together with the syllable standard pattern of the directly registered voice from the microphone (3).

In this third method, the sound recorded on the recording/playback device (2) is subject to the frequency characteristics of the recording/playback device (2), so the standard pattern created from the recorded sound and the microphone (3) When comparing the standard pattern created from the voice input directly from the standard pattern, differences appear between the two standard patterns. Therefore, when recognizing a recorded voice, it is necessary to use a standard pattern created from the recorded voice, and the microphone (3)
When you want to recognize the voice input directly from the microphone (3)
), it is necessary to use the standard pattern created from the voice input directly from the microphone (3), so by using the method described above, both the standard pattern registered directly from the microphone (3) and the standard pattern created from the recorded voice can be used. Patterns can be created and stored with a single voice registration operation. In addition, if the registered voice is recorded in the recording and playback device (2), this recorded voice can be played back and input on the digital cheating machine for which no standard pattern has been created, without requiring the registrant's voice input. Standard patterns can be created simply by Also, if you record the registered voice on the recording and playback device (2) and record the text after this registered voice, you can connect this recording and playback device (2) to the main unit (100) later and record it. Everything from voice registration to sentence creation can be done automatically just by playing the recorded voice.

Note that the registrant's voice input for creating the standard voice pattern is performed by the registrant reading out the characters that the present device displays on the display device (6) in a fixed order.

In addition, a recording and playback device a<2 with a display function dedicated to this machine is also available.
) When using this recording/playback device (2), even when you carry it with you in Germany, you can utter the voice corresponding to the headword displayed on the display screen and record it on the recording/playback device (2).
It becomes possible to create standard patterns.

As mentioned above, when the registered voice for which a standard pattern is to be created is recorded in the recording/playback device t(2), the recorded voice may be affected by noise etc. when creating the standard pattern from the recorded registered voice. There is a possibility that there is a difference between the headword and the corresponding headword, and for the sake of explanation, a case will be described below based on FIG. 9 in which a tape recorder is used as the recording/playback device. Figure 9(a) shows the registered voice ``A''~ corresponding to the heading ``A~~''Ka, of the registered voices recorded on a tape recorder for standard pattern creation.
It represents the state of the tape between “ka” and here “
As shown in Figure 9 (a), which shows the case where [noise] was recorded between "e" and "o", the voice was registered using a tape in which [noise] was recorded between the registered voices. If you do this, the input registered voices will be changed simply by the order of the sounds recorded on the tape, such as the first recorded sound being "a" and the second recorded sound being "i". When determining which syllables correspond to the syllables, the actual input registered speech and the entry word become misaligned because even Noiseco is considered to be a registered speech and the entry word is made to correspond.

Here, FIG. 9(b) incorrectly recognizes [noise] as voice,
This is a diagram in which [noise] is input to the headword 1e, and the syllable ``e'' is input to the headword 1o.

In this way, when creating a standard pattern from registered voices, the recorded voice and headwords may deviate due to the influence of noise, etc., so the types of registered voices are indicated as shown in Figure 9 (C). The character code sounds obtained are recorded in a recording/playback device (2) in correspondence with the registered sounds. With this method, even if [noiseko] is recorded between "u" and "e", the difference between the input sound and the headword is prevented as described above.

A method of recording a character-code sound of a specific frequency to prevent this deviation will be explained separately for the case where the tape recorder of the recording/reproducing device (2) is a single track and the case where the tape recorder is a multi-track.

First, with reference to FIG. 10, a case will be described in which a recording/playback device with multi-track is used as the recording method.

When a multi-track recording/playback device is used as a recording method, the character code corresponding to the headword is recorded on a track on which no audio is recorded, as shown in FIG. 2(a). In the voice recognition unit (1), this character
From the code sound, we know the headword of the input voice, and among the sounds recorded on the audio track, we select the sounds recorded in the section t1 where this character-code sound is recorded, which have a sound pressure threshold or higher. Only those that meet the conditions are considered to be speech and analyzed.

Alternatively, as shown in FIG. 2(b), a character code corresponding to the headword is recorded at the beginning and end of the audio, and the character code that indicates the beginning of the audio is selected from among the sounds recorded on the audio track. Among the sounds recorded in the interval t2 between the character and the chord sound indicating the end of the voice,
Only those that satisfy the condition of being equal to or higher than the sound pressure threshold are regarded as voices and analyzed.

Alternatively, as shown in FIG. 5C, a character code corresponding to the headword is recorded at the beginning of the audio. Among the sounds recorded on the audio track, among the sounds recorded in the section t3 from the character-code sound indicating the type of sound to the character-code sound corresponding to the next headword,
Only those that meet the conditions equal to or higher than the sound pressure threshold are considered to be voices and analyzed.

In the case of a single-track recording/playback device (2), the second method is to represent the character code corresponding to the headword as a sound outside the analysis frequency band of the a-voice, and place it on the track where the audio has been recorded along with the audio. Record. The method for recording character chord sounds in this case is the same as in the multi-track case described above. In other words, the above tl, t
2. Among the sounds recorded in the interval t3, only those that satisfy the same conditions as described above are regarded as voices and analyzed.

However, except in the case of the embodiment shown in E(a) where the voice and the character code sound overlap, the character code sound overlaps with the sound.
It is not necessary to use a sound outside the voice analysis frequency band as a chord sound.

Next, the simple and simple recognition section (13), such as alphabets, numbers, parentheses, and punctuation marks, etc., is selected in advance! (XS
The word standard pattern corresponding to the word registered as a character in d) is stored in the word standard pattern memory (13) in the figure.
c) Register.

First, by a predetermined operation, the parameter buffer (L3a) shown in FIG. 6 and the word standard pattern memory (L3c) are connected by the switch (13sl) to set the word registration mode.

Next, alphabets, numbers, parentheses, punctuation marks, etc. are displayed on the display device (6) of the main body (100) of the apparatus, and the operator inputs the reading corresponding to the north by voice.

The speech recognition section 1) analyzes this speech and registers the word standard pattern in the word standard pattern memory (13c).

Voice recognition becomes possible by performing the operations described above.

However, when you want to recognize a word that is not in the independent word/adjunct word dictionary (14a) or the word dictionary <13d),
It is necessary to register the word to be recognized in the supplementary i-word dictionary (14e), or to register the word to be recognized in the terminology dictionary (<13d), and the word standard pattern in the word standard pattern memory (13c). However, independent word/attached word dictionary (14
Whether to register the word in e) or to register the word and word standard pattern in the word dictionary (13d) and word standard pattern memory (13c) depends on whether the user wants to recognize the word as a clause utterance or the word Determine whether you want it to be recognized as a vocalization.

In addition, if the word is in the independent word/adjunct word dictionary (14e) but not in the word dictionary (13d) and you still want to recognize it by word recognition, you can add the word to the word dictionary (13d) and word standard pattern memory (13c). , the word and the word standard butter> need to be registered.

The method for registering arbitrary words will be described below.

To register the 81 words, enter the words in the independent word / attached f / Ik word dictionary (
There are two methods: registering a character string in 14e), and registering a word standard pattern for N words in a word standard pattern memory (13c), and registering a character string in a word dictionary (13d).

When registering a word in the independent word/adjunct word dictionary (14e), the word to be registered is uttered and input into the device.

At this time, this device recognizes this voice with the voice recognition unit (1) and displays the recognition result! Displayed in (6). If the result is correct, the user presses a predetermined key on the keyboard (7>) and registers the uttered voice as a character string displayed on the display device (6) in the independent word/adjunct word dictionary (14@). If the recognition result displayed on the display device (6) is not correct, use the syllable correction function of this device to correct the recognition result displayed on the display device (6) or re-speak the #L word you want to register. do. If the re-uttered result is incorrect, it is corrected again using the syllable correction function of this device. The above operations are repeated until the character string displayed on the display device t(6) matches the word to be registered.

When registering a word in the word standard pattern memory (13c) and word dictionary (13d), the display device (
6) Display the character string you want to register correctly. Next, the correctly recognized character strings and word standard patterns are stored in a word dictionary (
13d) and It word standard pattern memory (13c).

In addition, recognizing natural voice input is
Considering the current level of speech recognition technology, this is unreasonable. Since the current level of speech recognition technology is limited to continuous syllable utterance input, an example of continuous syllable utterance input will be described below.

In the case of continuous syllable vocalization input, the above procedure is the same, but in the case of continuous syllable vocalization input, the word standard pattern is also a continuous syllable vocalization pattern, so the word you want to register can be re-uttered naturally. , a word standard pattern is created by natural utterance, and the word standard pattern and character string are registered in the word standard pattern memory (13C) and the ms dictionary (13d), respectively.

With the above operations, the data necessary for creating sentences using voice recognition has been registered.

(i) Text creation An example of text creation will be described below.

First, when performing a recognition operation, the switch (13sl) of the word recognition unit (13) is set to the parameter buffer (13g).
The switch (14sl) of the phrase recognition section (14) is set so as to connect the parameter buffer (14a) and the syllable recognition section <14b), so that the word determination section (13b) is connected to the parameter buffer (14a).

There are two ways to create sentences.

The first method is an online recognition method in which the text to be created is directly input into the main body of the device by voice from the microphone (3).

The second method is to use a recording/playback device that records the text (2).
This is an offline recognition method in which the device is connected to the device, the recorded text is played back, and the text is recognized.

First, an example of online recognition will be described.

In the case of online recognition, sentences uttered in phrases or words are directly input into this device from the microphone (3), so by performing a prescribed operation, the microphone (3) and the voice recognition Connect (1).

Also, if you want to record the audio input from the microphone (3) on the recording/playback device (2), use the recording/playback device! (2
) to the main unit, and connect the input switching section (4) to the microphone (3).
) and the recording terminal of the recording/playback device (2).

At the same time, when a silence detection signal is input from the feature extraction section (12) as described later, the input switching section (4) is configured to record a beep sound indicating a phrase or word break.
! function.

During speech recognition, a word recognition unit (13) and a phrase recognition unit (14) are used.
) is running.

The audio input from the microphone (3>) is sent to the preprocessing unit (11)
The input audio is processed to have characteristics suitable for audio analysis (for example, when the sound pressure of the input audio is low, the sound pressure is amplified using an amplifier), and the feature extraction unit
12).

In the feature extraction section (12>), as shown in FIG.
).

At the same time, the analysis unit determination unit (12b) of the feature extraction unit (12)
), based on the analysis results of the analysis section (12m), the beep sound (
The details are shown in the embodiment of off-line recognition described later. ) is detected, and when a silent section is detected, a silent section detection signal (b) is generated.

The parameter buffer (12c) which receives the silent section detection signal (b) sends the stored characteristic parameters to the word recognition section (13) and phrase recognition section (14), and erases the stored contents.

The feature parameters input to the language recognition unit (13) are stored in the parameter map y (13a) shown in FIG. The word determination unit (13b) compares the feature parameters stored in the parameter buffer (13a) with the II standard pattern memory (13c), and selects the feature parameters stored in the parameter buffer (13a) and words with a large likelihood. Words with standard patterns are added to the word dictionary (13d)
A plurality of words are selected, and the character strings of the selected words and their likelihood values are sent to the candidate creation section (15).

On the other hand, the feature parameters input to the phrase recognition unit (14) are stored in the parameter buffer (14a). In the syllable recognition unit (14b), the parameter buffer (14a)
The characteristic parameters stored in the syllable standard pattern memory (14d) are compared, and the parameter buffer <14a) is compared with the syllable standard pattern memory (14d).
0 Phrase judgment unit <1 which converts the feature parameters stored in the syllable string into a syllable string and sends the syllable string to the Phrase judgment unit (14c).
In 4c), the input syllable string and the independent word/adjunct word dictionary (1
Compare the words registered in 4e), combine independent words and adjunct words to create multiple sets of clauses with a high likelihood, and send the character strings of the created clauses and their likelihood values to the candidate creation unit (15). send to

The candidate generation unit (15) selects a plurality of strings with the highest likelihood from the input character strings, and uses the likelihood value and the data sent from the word recognition unit (13) or the phrase recognition unit (14). A code indicating whether the data is received is added and stored. at the same time,
A signal is sent to the control unit (5) to display the character string with the greatest likelihood on the display device. Upon receiving this signal, the control unit (5) adds a delimiter mark "7" after the character string with the highest likelihood, and for example, for the input sentence in FIG. 14(a), the character string shown in FIG. 14(C) is Display it on the display device in the format shown in . At the same time, the candidate creation section (15)
), a signal is sent to cause the content stored in the candidate generation unit (15) to be stored in the storage device (8). The control unit (5) receives this signal and stores the character string stored in the candidate creation unit (15) in the storage device (8) in the form of a code representing a delimiter added after the character string. The character string stored in this external storage device is assumed to be the primary manuscript of the word processor. Generally, a floppy disk is used, but in this case, the file format of the storage device (8) must match the file format of the workbook.

Further, the signal generating section (42) of the input switching section (4) shown in FIG. 8, which receives this silent section detection signal, generates a beep sound representing the break between clauses or words of the sentence, and switches the beep sound. Enter in (41). The switch (41) connects a circuit so that the audio input from the microphone (3) and the beep sound input from the signal generator (42) are recorded on the recording/playback device (2). (2) A beep sound is recorded in the silent period that is considered to be a break between phrases or words in the recorded sentence.

Next, an example of offline recognition will be described.

For offline recognition, this device is equipped with a recording/playback device (2).
Since the text is created by playing back and inputting the recorded voice, the text is first recorded on the recording/playback device (2).

Also, a recording playback bag! (2) To perform more voice input,
The input switching unit (4) connects the recording/reproducing device (2) and the voice recognition unit (1).

When recording sentences, the system vocalizes phrases or words, creating silent intervals between phrases and words. Also, a recording and playback device exclusively for this device as shown in Figure 1! When using (2), in order to clearly mark the divisions between phrases and words, use the recording/playback device (2) or the division key (7
1) Press to record.

In addition, the registered words are uttered word by word, but if the recording/playback device (2) has a character sound generation function and has a character corresponding to the word you want to input, that voice will be used instead of the voice. Character sounds may also be recorded.

In addition, signals indicating the beginning and end of a sentence are recorded together with the voice in order to prevent noise recorded between sentences at the beginning of each sentence from being mistakenly recognized as voice.

However, the method of recording this signal changes depending on whether the recording/reproducing device (2) is a multi-track system or not, as described in the audio registration section. FIG. 11 shows a multi-track system and FIG. 12 shows a single-track system. FIGS. 11(a) and 12(a) show a method of detecting a section in which a sound such as a DTMF signal is recorded as an audio region.

Figures 11 (b) and 12 (b) show that a sound such as a DTMF signal is recorded before a sentence begins, and then recorded again when the sentence ends, and the section between these two signals is recorded. This is a method of detecting it as a voice area.

Furthermore, in the case of the single track system shown in FIG. 12, a DTMF signal or the like outside the audio band is used, considering that the audio section and the sound such as the DTMF signal overlap.

Furthermore, when recognizing a sentence, the sections t4 and t5 before and after the recorded signal are sampled, and in order to determine whether or not it is voice, it is not always necessary to identify the beginning of the sentence and the beginning of the signal, and the end of the sentence and the end of the signal. They do not need to match, so recognition is possible even if there is a slight lag between the timing at which the sentence is uttered and the timing at which the key is pressed.

Next, the recording/playback device (2) is connected to the main body of this device and the recorded voice is played back to perform recognition processing, but before recognizing this recorded voice, the recognition speed mode is set to a high playback speed of the recorded voice. If you have time and need a high recognition rate, you can select either the fast recognition mode that shortens the recognition time, the mode that recognizes at normal playback speed, or the double playback recognition mode if you have plenty of time and require a high recognition rate. Set it to mode.

First, an example of the fast listening recognition mode will be described.

! ? ! In the listening recognition mode, the playback speed of the recorded sound is increased, so the characteristics of the input sound are different from the standard pattern created from the registered sound played back at the normal playback speed. Even if the voice is input at a faster speed, the voice recognition cannot be performed accurately.

Therefore, in order to accurately recognize audio that has been played back at a faster speed, the sampling frequency is changed. Examples of such methods are described below.

The sampling frequency control unit (12d) of the feature extraction unit (12) in FIG. Recording speed) to sample and analyze the audio. Feature extraction part (12
) The subsequent processing is the same as in the example for online recognition, except that a beep sound indicating the break between phrases and words is input into the recorded text of the recording/playback device (2). However, when the feature extraction unit (12) detects such a beep sound, the feature extraction unit (12) generates a beep sound detection signal (l) instead of the silent section detection signal (b).
occurs. If the received signal is not the silent section detection signal (b) but the beep sound detection signal (b), the input switching section (
The signal generating unit (42) of 4) does not generate a beep sound representing a break between clauses or words of a sentence.

Further, when the speech recognition unit (1) recognizes a character-sound indicating a word, it outputs a word corresponding to the character-sound as a recognition result.

Next, an example of the twice playback recognition mode will be described.

In this mode, recorded audio is played back and input to the device.

At this time, the preprocessing unit (11) of the voice recognition unit (1) reads all the sound pressure fluctuations of the recorded voice and stores this data in the back pressure fluctuation memory (Llb) shown in Fig. 4. Play the audio and input it to this device. At this time, the preprocessing unit (11) uses the data stored in the sound pressure fluctuation memory (llb) to determine the input sound pressure to the feature extraction unit (12), which is most suitable for speech recognition, as shown in FIG. Adjust the amplification factor of the AGC circuit (LLa) to match the level.

That is, the gain G is fixed to the control voltage V. (variably adjusted).

Further, as another example of the twice playback recognition mode, a multiple playback recognition mode can also be considered. This involves playing and inputting a recorded sentence many times, changing the recognition method in the speech recognition unit (1) each time, comparing the recognition results, and selecting the one with the greatest likelihood of certainty. This is the way to do it.

In addition, if the recording/playback device (2) does not record the audio for registration, and depending on the recording/playback device (2), the frequency characteristics when the playback speed is increased are different from those at normal playback speed. or when making a recording/playback device (2) that has a different frequency characteristic than the recording/playback device (2) used to create the standard voice pattern recognize a recorded sentence, or when used to create the standard voice pattern. A recording/playback device that has the same standard frequency characteristics as the recording/playback device (2), but whose actual frequency characteristics are different from those of the recording/playback device (2) used to create the standard audio pattern due to the influence of errors in the parts used. When making the device (2) recognize recorded sentences, a function for correcting the influence of frequency characteristics described below is used.

First, a reference sine wave signal is generated by the reference signal generator (42
) and record it in the recording/playback bag e(2). After that, the recorded reference sine wave signal is reproduced and input to the present device. The input reference sine wave signal is sent to the speech recognition unit (1).
analyzes and determines the difference in frequency characteristics between the recorded reference sine wave signal and the reference sine wave signal generated by the reference signal generator (42), and compares the recorded reference sine wave signal with the reference signal generator (42). Correction is applied to reduce the difference in frequency characteristics from the reference sine wave signal generated in (42). There are many ways to apply the correction, depending on the feature extraction method of the feature extraction unit (12) of the speech recognition unit (1). For example, as shown in FIG.
If it is an analog filter bank system consisting of a parallel connection of an amplifier (AMP) and an amplifier (AMP), the reference signal generator (42) can be adjusted by adjusting the amplification factor of the amplifier (AMP). The output from the filter is adjusted so as to reduce the difference in frequency characteristics from the generated reference sine wave signal. In addition, if a digital filter is used as the feature extraction method of the feature extraction unit (12), the parameters that determine the characteristics of the digital filter may be changed. 1
Various methods can be considered corresponding to the feature extraction method 2).

By the above operations, the voice input text has been converted into a string other than the text. A correction method when the kana string-converted text differs from the input text will be described below, using FIG. 14 and classifying each case into error. Correct it using the following steps.

Figure 14 (a) is the input text, Figure 14 (b) is the input voice, Figure 14 (c) is the recognition result, Figure 14 (d) to (h) are the correction process,
Figure (1) shows the correction results.

First, we will discuss a correction method when a word uttered is incorrectly recognized as a phrase. As shown in Figure (C), when the word "C" uttered is recognized as the phrase "shi-", first move the cursor <X) to the part of the incorrect word [Figure (d) )i], Next, press the word next candidate key (72) to display the next candidate for the word [(d) i in the same figure.If this result is correct, proceed to the next correction part.If this result is incorrect, proceed to the next correction part. For example, press the word next candidate key (72) again to display the next word candidate. Repeat this operation until all correct answers are displayed.

Next, we will discuss how to correct a phrase uttered as a phrase that is misrecognized as a word.If the phrase uttered as a phrase ``i'' is recognized as the word ``E,'' first, if the cursor (X) is Next, press the phrase next candidate key (73) to display the next phrase candidate. If this result is correct, proceed to the next modification part.

If this result is incorrect, the phrase next candidate key (73)
Press to display the next phrase option. Repeat this operation until the correct answer is displayed.

It is also possible to display the previous candidate for a word by pressing the pre-word candidate key (74), and the previous candidate for each phrase by pressing the pre-phrase candidate key (75).

If the correct answer cannot be obtained using the above two correction methods, correction may be performed in units of syllables, or words, phrases, or syllables may be re-inputted.

In addition, in order to avoid recognizing phrases as words or recognizing words as phrases again during re-voice input, the candidate generation section (15) is configured to only recognize the recognition results sent from the word recognition section (13). As a recognition result, phrase recognition unit (14)
￥I sent from! The detection results can be controlled externally to be ignored.

In addition, the candidate generation unit (15) is configured to receive an external signal so that only the recognition results sent from the phrase recognition unit (14) are regarded as recognition results, and the recognition results sent from the word recognition unit (13) are ignored. Can be controlled.

The next candidate key mentioned above is a key having the function described below, and will be explained using FIG. 15.

In the speech recognition unit (1) of this device, word recognition and phrase recognition run in parallel, and as mentioned above, the re-recognition results for words and phrases are obtained. The phrase next candidate key (73) is the key for displaying the recognition results on the display device (6) in order from the highest likelihood to the recognition result, and displays the recognition results in the order from highest to lowest likelihood. The key to display the recognition result on the display device is the word next candidate key (72), which displays the recognition result with one higher likelihood than the recognition result currently displayed on the display device on the display device (6). The keys to be displayed are the pre-word candidate key and the pre-phrase candidate key.

FIG. 15 shows the candidate buffer (15a) of the candidate creation section (15).
), this figure shows that the recognition result in the - position is ``tango,'' and that this is the recognition result sent from the word recognition unit <13). Similarly, the recognition result of the third place is 'Tango wo', and this is the recognition result sent from the phrase recognition unit (14), which is represented by (clause), and the recognition result of the third place is 'Tango wo'. “Tangoni” and
This is a recognition result sent from the phrase recognition unit (14), which is represented by (clause), and the fourth recognition result is ``Tankou.''

This is the recognition result sent from the word recognition unit (13), which is represented by (word).

It is now assumed that rtango is displayed on the display device (6) and the temperature is ℃. In this state, when the phrase next candidate key (73) is pressed, the display device (6) displays ``Matamago wo''. Also, if you press the next word candidate key (72), the display will display rlt (6).
“Tankou,” is displayed.

Also, display! In (6), when "tankou" is displayed, if you press the pre-word candidate key (74), "tango" will be displayed on display device 1 (6), and the pre-phrase candidate key (
73), the display device (6) will display ``Matagoni''.

Next, we will discuss how to modify an entire passage at once.

The example in FIG. 14(e) is an example in which the word "rT" is incorrectly recognized as r A . First, move the cursor to the word you want to correct [(e)il in the same figure.Next, press the word next candidate key (72) to display the next candidate for the word [(e)i in the same figure]. If this result is correct, proceed to the next part to be corrected; if this result is incorrect, press the @word style candidate key (72) to display the next word candidate.

Repeat this operation until the correct answer is displayed. If the correct answer is not displayed, it is possible to display the previously displayed word candidate by re-speaking and re-inputting, or by pressing the previous word candidate key (74).

Next, we will discuss how to correct an entire word at once.

The example in FIG. 14(f') is an example where the phrase "gamen no" is mistakenly recognized as "gainen no ko." First, move the cursor to the phrase you want to correct [FIG. 14(f)il.

Next, press the phrase next candidate key (73) to display the next phrase candidate [(f') in the same figure. If this result is correct, proceed to the next correction part; if this result is wrong, proceed to the next phrase candidate. Press the candidate key (73) to display the next candidate for the phrase.

Repeat this operation until the correct answer is displayed. If the correct answer is not displayed, re-speak and re-enter. By pressing the previous clause candidate key (75), display the candidate clause for the previous clause displayed. You can also do it.

Next, a method for correcting syllables will be described.

The example in Figure 14 (h) is an example where the phrase ``Onseide'' is incorrectly recognized as ``Onkeide.'' In this example, the syllable ``ke'' is to be corrected to ``rse'', but first the cursor is Move (X) to the syllable ``ke'' that you want to correct, and then press the syllable next candidate key (76). The section a with the closest one is displayed [Figure (h) iL If the correct answer is displayed, move on to the next correction section. If this result is wrong,
Press the syllable next candidate key again to display the next syllable candidate.

Repeat this operation until the correct answer is displayed. If the correct answer is not displayed, re-enter by re-speaking. If the re-input results are incorrect, correct them again using the steps above. Repeat this operation until the correct answer is displayed.

Furthermore, by pressing the previous syllable candidate key (77), the previous syllable candidate can be displayed.

If you want to delete a syllable, move the cursor to the syllable you want to modify and press the delete key (78) to delete it.

When you want to insert a syllable, move the cursor to the syllable you want to modify and press the insert key (79) to insert it.

Next, using FIG. 16, the several syllable correction method will be described.

In this example, the input sentence ``Kaijiyo'' shown in FIG. In this case, first move the cursor (X) to the syllable you want to correct [Figure (C)] and enter "kai" again and again. The re-voiced input speech is recognized by the speech recognition section (1), and the recognition result is displayed on the display device (6). If the recognition result is correct, proceed to the next correction section. As shown in Figure (d), if "kai" is mistakenly recognized as 1 kae J, if it is a word, press the word next candidate key (72). If it is a 0 phrase, press the next phrase candidate key (72). 73). Since Figure 16 is an example of a word, the following describes how to correct a word.If you press the word next candidate key (72) in the state shown in Figure 16(d), first press the control button. Part (5) uses the word dictionary (13d) to compare the recognition result 1 in the figure (b) before correction with the recognition result 1 in the figure (d) after re-voicing. , the control unit (5) finds the same part "JIYO" at the 0th order,
From the word dictionary (13d), select a word that has the same part "jiyo". The figure (f') is a word dictionary! ! (13d)
(g) shows the zero-order control unit (
5) calculates the likelihood between the word written in (g) of the same figure and the recognition result 1 after reuttering, and displays the word with the largest likelihood value [(e of the same figure) )].

Next, we will discuss the case of correcting recognition boundary errors of phrases or words.

In the example in Figure 14 (g), the word ``bun'' and the phrase ``r'' are mistakenly recognized as having a silent section between the phrase ``bun'' and ``1'', as indicated by the Cvl mark.

This is an example of a misrecognition of two parts.

In this case, the recognition boundary error must be corrected, but if you want to delete the recognition boundary delimiter, move the cursor (X) over the recognition boundary delimiter you want to delete [see figure (g)
il, press the delete key (78>) [FIG.

However, as will be described later, the delimiter beep of the recording/playback device (2) and the delimiter added to the recognition result stored in the storage device (8) are different from the recording/playback device (2) and the memory device!
This will serve as a landmark for synchronizing <8>, so it must be prepared accordingly. Therefore, at this time, the storage device (
The storage device (8) indicates that the delimiter has been inserted and deleted in the storage device (8).
).

For example, the sentence shown in Figure 14 (g) 1 is
g) Assume that the information is stored in the storage device (8) as shown in i. When the sentence in (g)i is modified as shown in (g)i, the delimiter "7" that was completely stored in the storage device 8) is changed to the symbol "1ma". symbol "ma"
is a symbol indicating that the delimiter 17'' has been deleted, and is not used as a symbol indicating a recognition unit, but is used only for controlling the recording/reproducing device t(2) or the like.

With this configuration, even after deleting the delimiter "ma", the beep sound recorded in the recording/playback device (2) and the symbol "1ma", "ma," stored in the storage device 1 (8>) By using , both devices can be controlled in synchronization.

The above is an example where the delimiter "1ma" is deleted, but the same idea can be applied when it is inserted. In other words, a specific symbol that is not used as a control signal and represents only a delimiter may be inserted in place of the delimiter 17°.

By the above correction procedure, as shown in Fig. 14 (1),
Correct the text.

After the recognition boundary error has been corrected, the recognition unit for which the recognition boundary error has been corrected is corrected according to the correction procedure. In the case of correction by re-voicing, the voice of anyone who has registered the standard Bakun can be recognized, so corrections can be made even if the person is not the person who recorded the text.

The method for correcting kana string sentences has been described above, and the following functions are provided to assist in correction.

By moving the cursor on the character string displayed on the display device (6) and scrolling the display screen, storage device 1<8>
The stored sentences can be displayed more sequentially on the display screen, and at this time, the audio corresponding to the portion displayed on the screen is played back from the recording/playback device (2).

It also has the opposite function to the above-mentioned Ja Noh, and the character string corresponding to the part being played back from the recording/playback device (2) is displayed on the display device 1! (6) is displayed.

In addition, in both of the above methods, the time before the delimiter recorded in the recorded text and the delimiter recorded on the display side are used as timing signals for synchronization, and the playback of the recording and playback device (2) is performed. and the display are controlled so that they operate in synchronization with each other. Also, the keyboard (7
), or when a signal to stop the playback is input from the recording/playback device (2), the playback is stopped and the scrolling of the display or the movement of the cursor is also stopped.

Due to the synchronization function between the playback and display of the recording and playback device (2) further north, character strings can be checked while listening to the playback sound, making it easier to find corrections.

As for the synchronization method described here, the character string in the storage device (8) corresponding to the part being played back is transferred to the display device 6.
〉 How to display the Kana column of the part that is delayed by one delimiter from the part that corresponds to the part that is being played! (
6) is a display method.

In this case, when the display is stopped for correction, the corrected part of the recorded voice has already been played back, so in order to play the corrected part again, it is necessary to locate the beginning of the part to be corrected from the reproduced text. Therefore, when this method is adopted, the recording/reproducing device (2) is provided with a function of automatically backtracking to the previous delimiter when the display is stopped.

In addition, when a tape recorder is used as the recording/playback device (2), the playback section is controlled by the rotation of a motor, and the beginning of the section corresponding to the correction section may not be accurately located due to slack in the tape, etc. There is.

In such a case, the input audio should be stored as a PCMQ sound or ADPCMI sound for a certain period of time, and if you want to listen back to the input audio, you can use PCM recording or ADP
Add a function to listen back to CM recorded audio.

FIG. 17 shows an embodiment of the above-mentioned functions, and numbers 01 to 05 in FIG. 0, which is a diagram of a PCM data memory for storing PCM recording data, indicate addresses. The input voice is the sentence "I put 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 for 1 1 1 1 1 1 for 1 1 1 for for 1 1 1 1 to 1 for 1 to 1 to 1 to 1 to 1 to 1 to 1 to 1 to 1 to 1 For" as shown in Figure 14. be.

When the above audio is input, PCM data memory C
DM), the voice "Washiwa" up to the first silent section is stored at address 01. The voice "ten" up to the second silent section is stored at address 02. The voice "te-" up to the fifth silent section is stored at address 05. At this time, P
The CM address pointer (AP) stores the address of the data stored first among the data stored in the PCM data memory. In this example, 01 can be stored.

At this stage, the PCM data memory is full.

Next, when audio is input, the PCM data memory (
0 to store the input voice at the address of the data stored first among the data stored in DM).
In this example, "1 Kamen's" is stored at address 01 where "Washiwa" was stored. At this time, the PCM address pointer (AP) is set to the data stored in the PCM data memory <DM>. In this example, 02 is stored as the address of the first stored data.

In this state, when reproducing the contents of the PCM data memory (DM), the contents are reproduced from the address pointed to by the PCM address pointer (AP). In this example, 02, 03,
It will be played back in the order of 04, 05, and 01.

With this method, it is possible to listen back to the audio accurately and quickly as many times as desired.

Also, move the cursor (X) to the recognition unit delimiter on the screen.
) and press the start key (70) of the recorded voice to find the part behind the delimiter on the recording/playback device (2) side that corresponds to the recognition unit indicated by the cursor in the recorded sentence, and then select the following sentence. The function to play is on the right side. An example of such a 1a old man is shown below.

To confirm the recognized sentences, the recognition results are stored in a storage device (8)
Read more, display device r! t, (6) is displayed from the beginning. At this time, the delimiter counter (5a) of the control unit 5) in FIG. 19 counts the number of delimiters read out from the storage device 1 (8). If so, place the cursor on the incorrect part and press the cue key.The control unit (5)
2) Play the recorded text in fast forward playback mode. Beep counter (1) of feature extraction unit (12)
Step 2e) counts beeps indicating breaks in a sentence inputted from the recording/playback device ff(2).

The comparison circuit (5b) has a beep counter (12e) (
7) When the value becomes one smaller than the value of the delimiter counter (5a) mentioned above, a signal (c) is sent to the recording/reproducing device (2) to stop the reproduction.

In addition, in order to confirm the recognition result and the corrected text, the data stored in the storage device (8) can be displayed on the display [(6)].
It is very tiring for the eyes because the user has to visually follow and read the string displayed on the display screen.

In view of this, this device has a function to read out the character strings stored in the storage device (8) in which the recognition results are stored using a voice synthesis function. , the recognition results, and the corrected text can be confirmed by listening to the synthesized speech.

In this case as well, the delimiter is used as a timing signal for synchronizing the speech synthesis unit 9), the storage device 8, the recording/reproducing device 2, and the display device t(6).

In other words, a character string corresponding to the part read out from the storage device (8) by the speech synthesis unit (9) is displayed on the display device (6), and at the same time, the recording part is cued up by the recording/playback device (2). . With this method, when an error is discovered by the read-aloud function of the speech synthesizer J and the read-aloud function of the speech synthesizer is stopped to correct it, the display device (6) also displays the recorded portion of the recording/playback device t(2). also shows the error part,
Corrections can be made instantly.

The method of synchronization described here is to display the kana column of the storage device that corresponds to the part that is being read out by the speech synthesis function! (6) At the same time, the method of reproducing the corresponding part of clause a from the sentence recorded in the recording and playback device (2), and the part corresponding to the part being read out by the speech synthesis function, the delimiter - There is a method of reproducing a portion of the text recorded on the delayed recording/reproducing device (2). In the latter case, when voice synthesis is stopped for correction, the recording/playback device (2) has stopped a little further than the part to be corrected, so if it is played back in this state, the corrected part of the audio can be immediately played back. In the former case, when voice synthesis is stopped for correction, the corrected part of the recorded voice has already been played back, so it is necessary to backtrack in order to play the corrected part again. Therefore, when adopting the former method, when the display is stopped, the recording and playback device (2
) preferably has the ability to backtrack to the previous delimiter.

In the above, an embodiment has been described in which the recognition results are stored in the storage device 1t (8), but as another embodiment, the recognition result may be stored in the recording and reproducing device (2).

In this way, if the recognition results stored in the storage device (8) are recorded in the recording/playback device (2) where the original text was recorded,
Since the original text and recognition results can be recorded on the same recording medium, management of the original text and recognition results becomes easier.

Furthermore, by recording the recognized results in the recording/reproducing bag e(2) while reproducing and inputting the recorded sentences, an external storage device is not required.

Even in the case of an audio recording/reproduction device f(2) of the multi-track type, it is possible to store the recognition results in the tracks where the audio has not been recorded while reproducing the recorded audio.

(g) Effects of the Invention According to the text creation system of the present invention, the silent section detection signal recorded in the recorded text and the delimiter recorded in the storage device are used as timing signals for synchronizing the recording. Since the playback and display of the playback device operate in close synchronization, the recorded audio corresponding to the portion displayed on the screen can be played back from the recording and playback device without any deviation, making it possible to listen to the audio. You can check the text displayed on the screen while doing so.

[Brief explanation of the drawing]

Figure 1 is an external view of a daytime cheating machine that employs the voice recognition system of the present invention, Figure 2 is a configuration diagram of the daytime cheating machine, Figure 3 is a configuration diagram of voice recognition section a (1), and Figure 4 is a configuration diagram of the voice recognition section a (1). Figure 5 is a configuration diagram of the preprocessing unit (11), Figure 5 is a configuration diagram of the feature extraction unit (12), Figure 6 is a configuration diagram of the word recognition unit (13), and Figure 7 is a configuration diagram of the sentence recognition unit (14). ), FIG. 8 is a configuration diagram of the input switching unit (4), and FIG. 9 is a block diagram of the headword and 0! Figure 10 is a diagram showing the relationship between the sound system and killrafter sound, Figure 10 is a diagram showing the relationship between character sound recording methods and voice sections, Figure 11 is a diagram showing the recording method when the recording/playback device is a multi-track system, and Figure 12 is a diagram showing the relationship between the recording method and the kill rafter sound. A diagram showing the recording method when the recording/playback device is a single track system, Figure 13 is a diagram showing an example of a frequency correction circuit, Figure 14 is a diagram for correction in case of erroneous recognition, and Figure 15 is the inside of the candidate creation section (15). Figure 16 is a diagram showing an example of correcting several syllables at the time of erroneous recognition.
FIG. 17 is an explanatory diagram of the P and CM recording method, FIG. 18 is an explanatory diagram of the AGC operation, and FIG. 19 is an explanatory diagram of the delimiter counter. (1)...Speech recognition unit, (2)...Recording and playback device,
(3)...Microphone, 6)...Display device, (7).
...Keyboard, (8)...Storage device, (11)...
・Preprocessing section, (12)...Feature extraction section, (13)...
・Word recognition unit, (14)... Clause recognition unit, (lla)
...Variable gain amplifier, (llb)...Sound pressure variation memory.

Claims (1)

[Claims] (1) It has a speech recognition function that recognizes the input speech played by the recording and playback device in units of phrases, syllables, and words by using the silent sections recorded on the recording and playback device as the delimiters of recognition units. When a silent interval is detected, a silent interval detection signal indicating that a silent interval has been detected is recorded in the silent interval of the recording/playback device, and the result of speech recognition is stored in a storage device with a delimiter for each recognition unit. What is claimed is: 1. A text creation system comprising: a speech recognition device having a silent section detection signal and a delimiter to synchronize a text read from a storage device and displayed on a display device with audio from a recording/playback device.