JPH05234338A - Speech recognition apparatus - Google Patents

Abstract

PURPOSE:To enable the checking of record contents of a tape quickly. CONSTITUTION:In a voice reproducing section 5, a voice signal recorded on a tape 4 is reproduced to be supplied to a speech recognizing section 3. At the speech recognizing section 3, a key word contained in the voice signal is extracted and supplied to a display section 12 through a key word processing section 10. At the display section 12, the key ward contained in the voice signal recorded on the tape is outputted.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice recognition apparatus suitable for use in confirming the contents of voice recorded on a tape or a disk.

[0002]

2. Description of the Related Art For example, in a tape recorder,
The state of the meeting can be recorded on tape. At this time, the index signal can be recorded at an arbitrary position as needed. As a result, the index signal can be searched from an arbitrary position on the tape and reproduced from that position.

[0003]

However, in the conventional apparatus, if the contents of the information recorded on the tape cannot be understood, all the information recorded at the beginning of the tape must be reproduced for confirmation. There was a problem that it took time to confirm the recorded contents of the tape.

Therefore, there is a method of confirming the recorded content of the tape by increasing the playback speed of the tape, but even with this method, the content must be heard from the beginning to the end of the tape, which requires a considerable amount of time. There was a problem that it was necessary and made the user feel annoyed.

The present invention has been made in view of such a situation, and makes it possible to quickly confirm the recorded contents.

[0006]

A voice recognition apparatus according to claim 1, wherein a tape 4 as a recording medium for recording a voice, a keyboard 7 as a keyword input means for inputting a keyword, or a keyword voice input section. 11 and
A standard pattern memory 24 as a storage means for storing the keyword input from the keyboard 7 or the keyword voice input unit 11, and a keyword extracting means for extracting the keyword stored in the standard pattern memory 24 from the voice recorded on the tape 4. And a voice output unit 6 or a display unit 12 as an output means for outputting the keyword extracted by the voice recognition unit 3.

This voice recognition apparatus uses a keyword information storage unit 13 as a frequency storage unit for storing the appearance frequency of the keywords extracted by the voice recognition unit 3 and the appearance frequency of the keywords stored in the keyword information storage unit 13. Correspondingly, the keyword processing unit 1 as keyword processing means for supplying the keyword to the voice output unit 6 or the display unit 12.
0 and can be further provided.

[0008]

In the voice recognition device according to the first aspect, the keywords included in the voice recorded on the tape 4 are extracted, and the extracted keywords are output to the voice output unit 6 or the display unit 1.
Output from 2. Therefore, the recorded contents of the tape 4 can be confirmed quickly.

When the keyword can be supplied to the voice output section 6 or the display section 12 in accordance with the appearance frequency of the keyword, the recorded contents of the tape 4 can be confirmed more quickly.

[0010]

1 is a block diagram showing the configuration of an embodiment of a voice recognition apparatus of the present invention. The voice input unit 1 outputs a signal obtained by A / D converting the input voice, that is, a digitized voice signal to the voice recording unit 2 and the voice recognition unit 3. The audio recording unit 2 records the audio signal output from the audio input unit 1 on the tape 4. The audio reproducing unit 5 is a tape 4
The audio signal recorded in (1) is reproduced and supplied to the audio output unit 6 and the audio recognition unit 3. The audio output unit 6 is the audio reproduction unit 5
The supplied voice signal or the keyword supplied from the keyword processing unit 10 is converted into voice and output.

The keyword voice input unit 11 supplies the input voice as a keyword to the selection processing unit 9. The keyboard 7 is for typing a keyword as a character (character string), and the typed character is output to the keyword creating unit 8. The keyword creating unit 8 creates a keyword as a voice signal from the keyword as a character output from the keyboard 7 and supplies it to the selection processing unit 9. The selection processing unit 9 selects either the keyword supplied from the keyword voice input unit 11 or the keyword supplied from the keyword creation unit 8, and the voice recognition unit 3
And output to the keyword processing unit 10.

As shown in FIG. 2, the voice recognition section 3 is composed of an acoustic analysis section 21, an input pattern memory 22, a DP matching section 23, a standard pattern memory 24, and a word spotting determination section 25. Acoustic analysis unit 21
When a voice signal as a keyword is supplied from the selection processing unit 9, the keyword (voice signal) is subjected to frequency analysis processing such as linear prediction analysis processing to calculate a voice feature parameter (feature parameter series). , To the standard pattern memory 24. Standard pattern memory 24
Stores the characteristic parameter calculated from the keyword supplied from the acoustic analysis unit 21 as a standard pattern.

In addition, when the audio signal is supplied from the audio input unit 1 or the audio signal reproduced from the tape 4 by the audio reproducing unit 5 is supplied to the acoustic analysis unit 21,
A linear prediction analysis process is performed on the voice signal to calculate a voice feature parameter (feature parameter series), and the voice feature parameter is supplied to the input pattern memory 22. The input pattern memory 22 temporarily stores the characteristic parameter of the voice supplied from the acoustic analysis unit 21 as an input pattern.

The DP matching unit 23 calculates the pattern distance between the input pattern temporarily stored in the input pattern memory 22 and the standard pattern stored in the standard pattern memory 24 by DP matching. That is, the DP matching unit 23 sets one of the time axis of the standard pattern or the time axis of the input pattern, for example, the time axis of the standard pattern, to be the most similar to the input pattern which is the other pattern (the standard pattern). And the input pattern) so that the distance between the standard pattern and the input pattern (time-normalized distance) is artificially distorted. Then, the DP matching unit 23, together with the distance between the standard pattern and the input pattern, the position where the time axis of the standard pattern corresponds to the time axis of the input pattern when the distance is obtained, that is, the standard in the input pattern. The position of the pattern is supplied to the word spotting determination unit 25.

The DP matching unit 23 performs the above processing on all the standard patterns stored in the standard pattern memory 24, and determines the minimum distance in all the standard patterns and the position where the minimum distance is obtained. Obtained and supplied to the word spotting determination unit 25.

The word spotting determination unit 25 uses the DP
From the minimum distance in all the standard patterns supplied from the matching unit 23 and the position where it is obtained,
All the standard patterns included in the input pattern are extracted (recognized), and the keywords for the standard patterns are output to the keyword processing unit 10 (FIG. 1).

The keyword processing unit 10 includes a voice recognition unit 3
The appearance frequency of the keyword output from the (word spotting determination unit 25) is counted and written in the keyword information storage unit 13 together with the keyword. Further, the keyword processing unit 10 reads the keyword corresponding to the appearance frequency of the keyword stored in the keyword information storage unit 13 and supplies the keyword to the voice output unit 6 via the display unit 12 or the voice reproduction unit 5. The keyword information storage unit 13 stores the keyword supplied from the keyword processing unit 10 and the appearance frequency thereof. The display unit 12 displays the keyword supplied from the keyword processing unit 10 as an image (character).

Next, the operation for registering a keyword will be described. The keyword input from the keyboard 7 via the keyword voice input unit 11 or the keyword creation unit 8 is supplied to the acoustic analysis unit 21 and the keyword processing unit 10 of the voice recognition unit 3 via the selection processing unit 9.
In the keyword processing unit 10, the keyword supplied from the selection processing unit 9 is supplied to the voice output unit 6 via the display unit 12 or the voice reproduction unit 5 for input confirmation. On the display unit 12, the keyword input from the keyboard 7 via the keyword creating unit 8 is displayed as an image, and on the voice output unit 6, the keyword voice input unit 11 is displayed.
The input keyword is output as voice.

It should be noted that one keyword is used for the keyboard 7
If both are input with both the keyword input unit 11 and the keyword voice input unit 11, the keyword input by voice (the keyword input by the keyword voice input unit 11) can be confirmed as characters, and the keyword input by characters ( The keyword input from the keyboard 7) can be confirmed by voice. That is, one keyword is specified on the keyboard 7
If both are input with the keyword voice input unit 11, the keyword can be confirmed by both characters (images) and voice.

On the other hand, in the acoustic analysis section 21 of the speech recognition section 3, the speech signal as the keyword supplied from the selection processing section 9 is subjected to linear prediction analysis, and the characteristic parameter (characteristic parameter series) of the speech is calculated and standardized. It is supplied to the pattern memory 24. In the standard pattern memory 24, the characteristic parameter calculated from the keyword supplied from the acoustic analysis unit 21 is stored as a standard pattern.

As described above, the keyword is registered (stored) in the standard pattern memory 24.

Further, the operation of recording voice on the tape 4 will be described. The voice signal is A / D converted in the voice input unit 1 and supplied to the voice recording unit 2 and the voice recognition unit 3. In the audio recording unit 2, the audio signal supplied from the audio input unit 1 is recorded on the tape 4.

On the other hand, the speech signal supplied to the speech recognition section 3 is subjected to linear prediction analysis processing in the acoustic analysis section 21 to calculate a characteristic parameter (characteristic parameter series) of speech. Then, in the input pattern memory 22, the characteristic parameter of the voice supplied from the acoustic analysis unit 21 is temporarily stored as an input pattern.

In the DP matching unit 23, the pattern distance between the input pattern temporarily stored in the input pattern memory 22 and the standard pattern stored in the standard pattern memory 24 is calculated by DP matching. That is, in the DP matching unit 23, one of the time axis of the standard pattern and the time axis of the input pattern, for example, the time axis of the standard pattern, is artificially set so as to be most similar to the input pattern which is the other pattern. After distortion, the distance between the standard pattern and the input pattern (time-normalized distance) is obtained. Then, in the DP matching unit 23, together with the distance between the standard pattern and the input pattern,
The position where the time axis of the standard pattern corresponds to the time axis of the input pattern when the distance is obtained, that is, the position of the standard pattern in the input pattern is obtained and supplied to the word spotting determination unit 25.

In the DP matching unit 23, all the standard patterns stored in the standard pattern memory 24 are subjected to the above processing, and the minimum distance in all the standard patterns and the position where the minimum distance is obtained. Is calculated and supplied to the word spotting determination unit 25.

In the word spotting determination section 25, all the standard patterns included in the input pattern are extracted (recognized) from the minimum distance in all the standard patterns supplied from the DP matching section 23 and the position where the minimum distance is obtained. Then, the keyword for the standard pattern is output to the keyword processing unit 10 (FIG. 1).

In the keyword processing unit 10, the appearance frequency of the keyword output from the voice recognition unit 3 (word spotting determination unit 25) is counted and written in the keyword information storage unit 13 together with the keyword. Further, in the keyword processing unit 10, when the input of the voice to the voice input unit 1 is completed, the keyword is read out in accordance with the appearance frequency of the keyword stored in the keyword information storage unit 13 (for example, a preset keyword is set). Only keywords having a frequency equal to or higher than a predetermined reference value are read out) and supplied to the voice output unit 6 via the display unit 12 or the voice reproduction unit 5. In the display unit 12, the keyword processing unit 10
The supplied keyword is displayed as an image (character), and the voice output unit 6 outputs the keyword supplied from the keyword processing unit 10 as voice.

Next, the operation of reproducing the recorded contents of the tape 4 will be described. In the audio reproduction unit 5, the audio signal recorded on the tape 4 is reproduced and supplied to the voice recognition unit 3. In the acoustic analysis unit 21 of the voice recognition unit 3,
The audio signal recorded on the tape 4 is subjected to a linear predictive analysis process, and an audio characteristic parameter (characteristic parameter series) is calculated. Then, in the input pattern memory 22,
The characteristic parameter of the voice supplied from the acoustic analysis unit 21 is temporarily stored as an input pattern.

In the DP matching unit 23, the pattern distance between the input pattern temporarily stored in the input pattern memory 22 and the standard pattern stored in the standard pattern memory 24 is calculated by DP matching. That is, in the DP matching unit 23, one of the time axis of the standard pattern and the time axis of the input pattern, for example, the time axis of the standard pattern, is artificially set so as to be most similar to the input pattern which is the other pattern. After distortion, the distance between the standard pattern and the input pattern (time-normalized distance) is obtained. Then, in the DP matching unit 23, together with the distance between the standard pattern and the input pattern,
The position where the time axis of the standard pattern corresponds to the time axis of the input pattern when the distance is obtained, that is, the position of the standard pattern in the input pattern is supplied to the word spotting determination unit 25.

In the DP matching unit 23, all the standard patterns stored in the standard pattern memory 24 are subjected to the above processing, and the minimum distance in all the standard patterns and the position where the minimum distance is obtained. Is calculated and supplied to the word spotting determination unit 25.

In the word spotting determination section 25, all the standard patterns included in the input pattern are extracted (recognized) from the minimum distance in all the standard patterns supplied from the DP matching section 23 and the position where the minimum distance is obtained. Then, the keyword for the standard pattern is output to the keyword processing unit 10 (FIG. 1).

In the keyword processing unit 10, the appearance frequency of the keyword output from the voice recognition unit 3 (word spotting determination unit 25) is counted and written in the keyword information storage unit 13 together with the keyword. Further, in the keyword processing unit 10, when the input of the voice to the voice reproduction unit 5 is completed, the keyword is read out in accordance with the appearance frequency of the keyword stored in the keyword information storage unit 13, and the display unit 12 or It is supplied to the audio output unit 6 via the audio reproduction unit 5. In the display unit 12,
The keyword supplied from the keyword processing unit 10 is displayed as an image (character), and the voice output unit 6 outputs the keyword supplied from the keyword processing unit 10 as a voice.

[0033] Therefore, the tape 4, for example, "Hello, this is Ono., But is a matter of Nagaoka fireworks before this was talking, August 3, it is so become filled with hot spring inn most reservation near Nagaoka. This On that occasion, why don't we reserve a hot spring a little far from Nagaoka and go out on the JR to see the fireworks? And if the hot springs are full, I think a normal guesthouse is also good. " ) Is recorded in the standard pattern memory 24, for example, “Tokyo, Osaka, Nagoya, Ishikawa, Hokkaido,
Niigata, Nagaoka, Kashiwazaki, Kawasaki, Chofu, Ono, Ogawa, Oka, Tanaka, Suzuki, windsurfing, skiing, tennis, hot spring, drive, fireworks, reservation, product, hope, purchase, use,
Catalog, billing, schedule, time, 1, 2, 3, 4, 5,
When a keyword such as “6, 7, 8, 9, 0, month, day” is registered, the threshold of the frequency of appearance of the keyword is set to be once for a person's name and twice for other words. ,
The keyword “fireworks, hot spring, reservation” is output from the voice output unit 6 or the display unit 12. From this keyword, the outline of the content of the voice (message) can be inferred.

Further, in the keyword processing unit 10, not only the keyword and its appearance frequency are written in the keyword information storage unit 13, but also the keyword and its appearance frequency can be recorded in, for example, the header of the tape 4. .. This makes it possible to immediately output the keyword by referring to the keyword recorded in the header of the tape 4 and its appearance frequency during reproduction.

In this embodiment, the tape is used as the recording medium for recording the audio signal. However, if the audio signal is recorded on a disc such as an optical disc or a magneto-optical disc which can be randomly accessed, The keyword can be searched more quickly.

[0036]

According to the voice recognition device of the first aspect, the keyword contained in the voice recorded in the recording medium is extracted, and the extracted keyword is output from the output means.
Therefore, the recorded contents of the recording medium can be confirmed quickly.

According to the voice recognition device of the second aspect,
Since the keywords are supplied to the output means in accordance with the frequency of appearance of the keywords, it is possible to omit the output of the keywords having a low frequency, and to compare the recorded contents of the recording medium with the case of outputting all the keywords. Can be confirmed more quickly.

[Brief description of drawings]

FIG. 1 is a block diagram showing a configuration of an embodiment of a voice recognition device of the present invention.

FIG. 2 is a more detailed block diagram of a voice recognition unit 3 of the embodiment of FIG.

[Explanation of symbols]

 1 voice input unit 2 voice recording unit 3 voice recognition unit 4 tape 5 voice reproduction unit 6 voice output unit 7 keyboard 8 keyword creation unit 9 selection processing unit 10 keyword processing unit 11 keyword voice input unit 12 display unit 13 keyword information storage unit 21 Acoustic analysis unit 22 Input pattern memory 23 DP matching unit 24 Standard pattern memory 25 Word spotting determination unit

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Yuko Tanaka 6-735 Kita-Shinagawa, Shinagawa-ku, Tokyo Inside Sony Corporation (72) Inventor Yasuhiko Kato 6-35 Kita-Shinagawa, Shinagawa-ku, Tokyo Sony Corporation (72) Inventor Tetsuo Kobayashi 6-735 Kitashinagawa, Shinagawa-ku, Tokyo Sony Corporation

Claims (2)

[Claims] 1. A recording medium for recording a voice, a keyword input unit for inputting a keyword, a storage unit for storing a keyword input by the keyword input unit, and a voice recorded on the recording medium, A voice recognition device comprising: a keyword extraction unit that extracts a keyword stored in the storage unit; and an output unit that outputs the keyword extracted by the keyword extraction unit. 2. A frequency storage unit that stores the appearance frequency of the keyword extracted by the keyword extraction unit, and the keyword is supplied to the output unit corresponding to the appearance frequency of the keyword stored in the frequency storage unit. The voice recognition device according to claim 1, further comprising: