Method and apparatus of speech recognition and speech control system using the speech recognition method

• US 6,308,152 B1
• Filed: 06/22/1999
• Issued: 10/23/2001
• Est. Priority Date: 07/07/1998
• Status: Expired due to Term

• Current Assignee: Panasonic Intellectual Property Corporation of America (Panasonic Holdings Corporation)
• Original Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Inventors: Konuma, Tomohiro, Kuwano, Hiroyasu
• Primary Examiner(s): Dorvil, Richemond
• Application Number:
  US09/337,734
• Time in Patent Office: 854 Days
• Field of Search: 704/270, 704/275, 704/231, 704/238, 704/236, 704/239, 704/240, 704/251, 704/252, 704/255, 704/256
• US Class Current: 704/238
• CPC Class Codes: G10L 15/08 Speech classification or search

Abstract

A string of acoustic feature parameters of each of recognition-desired words and a string of acoustic feature parameters of each of reception words are registered in advance. When an uttered word is received, a string of acoustic feature parameters is extracted from the uttered word, the acoustic feature parameters of the uttered word is compared with the string of acoustic feature parameters of each recognition-desired word, and a recognition-desired word recognition score indicating a similarity degree between the uttered word and each recognition-desired word is calculated. Also, a reception word recognition score indicating a similarity degree between the uttered word and each reception word is calculated. In cases where a particular recognition-desired word recognition score corresponding to a particular recognition-desired word is higher than the highest reception word recognition score, the utter word is recognized as the particular recognition-desired word, and an operation of an electric apparatus is controlled according to the particular recognition-desired word. In contrast, in cases where a particular reception word recognition score corresponding to a particular reception word is higher than the highest recognition-desired word recognition score, the utter word is recognized as the particular reception word and is rejected, so that the electric apparatus is not operated.

Claims

1. A speech recognition method, comprising the steps of:

registering an acoustic feature of a recognition-desired word desired to be recognized for each of a plurality of recognition-desired words;

registering an acoustic feature of a reception word differing from the recognition-desired words for each of a plurality of recognition-desired words;

receiving an utterance including an uttered word;

calculating a recognition-desired word recognition score indicating a similarity degree between the uttered word and each recognition-desired word by comparing the acoustic feature of the recognition-desired word with an acoustic feature of the uttered word;

calculating a reception word recognition score indicating a similarity degree between the uttered word and each reception word by comparing the acoustic feature of the reception word with the acoustic feature of the uttered word;

recognizing the uttered word as a particular recognition-desired word corresponding to a particular recognition-desired word recognition score in cases where the particular recognition-desired word recognition score is higher than the highest reception word recognition score; and

rejecting the utterance in cases where the highest recognition-desired word recognition score is equal to or lower than the highest reception word recognition score.

2. A speech recognition method according to claim 1, further comprising the step of:

informing a user that the utterance is rejected in cases where the utterance is rejected.

3. A speech recognition method according to claim 1 in which the step of calculating a recognition-desired word recognition score includes the steps of:

analyzing the acoustic feature of the uttered word;

calculating a statistical distance between the acoustic feature of the uttered word and the acoustic feature of each recognition-desired word on a statistical distance scale; and

setting the statistical distance of one recognition-desired word as the recognition-desired word recognition score of the recognition-desired word for each recognition-desired word, and

the step of calculating a reception word recognition score includes the steps of;

calculating a statistical distance between the string of acoustic feature of the uttered word and the acoustic feature of each reception word on a statistical distance scale; and

setting the statistical distance of one reception word as the reception word recognition score of the reception word for each reception word.

4. A speech recognition apparatus, comprising:

recognition-desired word registering means for registering an acoustic feature of a recognition-desired word desired to be recognized for each of a plurality of recognition-desired words;

reception word registering means for registering an acoustic feature of a reception word differing from the recognition-desired words for each of a plurality of recognition-desired words;

word receiving means for receiving an utterance including an uttered word;

recognition-desired word recognition score calculating means for calculating a recognition-desired word recognition score indicating a similarity degree between the uttered word received by the word receiving means and each recognition-desired word registered by the recognition-desired word registering means by comparing the acoustic feature of the recognition-desired word with an acoustic feature of the uttered word;

reception word recognition score calculating means for calculating a reception word recognition score indicating a similarity degree between the uttered word received by the word receiving means and each reception word registered by the reception word registering means by comparing the acoustic feature of the reception word with the acoustic feature of the uttered word;

word recognizing means for recognizing the uttered word received by the word receiving means as a particular recognition-desired word corresponding to a particular recognition-desired word recognition score calculated by the recognition-desired word recognition score calculating means in cases where the particular recognition-desired word recognition score is higher than the highest reception word recognition score calculated by the reception word recognition score calculating means; and

utterance rejecting means for rejecting the utterance received by the word receiving means in cases where the highest recognition-desired word recognition score calculated by the recognition-desired word recognition score calculating means is equal to or lower than the highest reception word recognition score calculated by the reception word recognition score calculating means.

5. A speech recognition apparatus according to claim 4, further comprising:

rejection informing means for informing a user that the utterance received by the word receiving means is rejected in cases where the utterance is rejected by the utterance rejecting means.

6. A speech recognition apparatus according to claim 4, further comprising:

acoustic feature extracting means for extracting the acoustic feature of the uttered word from the uttered word received by the word receiving means, and

a statistical distance between the acoustic feature of the uttered word extracted by the acoustic feature extracting means and the acoustic feature of one recognition-desired word registered by the recognition-desired word registering means on a statistical distance scale is set as the recognition-desired word recognition score of the recognition-desired word for each recognition-desired word by the recognition-desired word recognition score calculating means, and

a statistical distance between the acoustic feature of the uttered word extracted by the acoustic feature extracting means and the acoustic feature of one reception word registered by the reception word registering means on a statistical distance scale is set as the reception word recognition score of the reception word for each reception word by the reception word recognition score calculating means.

7. A speech control system, comprising:

recognition-desired word registering means for registering an acoustic feature of a recognition-desired word desired to be recognized for each of a plurality of recognition-desired words;

reception word registering means for registering an acoustic feature of a reception word differing from the recognition-desired words for each of a plurality of recognition-desired words;

word receiving means for receiving an utterance including an uttered word;

recognition-desired word recognition score calculating means for calculating a recognition-desired word recognition score indicating a similarity degree between the uttered word received by the word receiving means and each recognition-desired word registered by the recognition-desired word registering means by comparing the acoustic feature of the recognition-desired word with an acoustic feature of the uttered word;

reception word recognition score calculating means for calculating a reception word recognition score indicating a similarity degree between the uttered word received by the word receiving means and each reception word registered by the reception word registering means by comparing the acoustic feature of the reception word with the acoustic feature of the uttered word;

word recognizing means for recognizing the uttered word received by the word receiving means as a particular recognition-desired word corresponding to a particular recognition-desired word recognition score calculated by the recognition-desired word recognition score calculating means in cases where the particular recognition-desired word recognition score is higher than the highest reception word recognition score calculated by the reception word recognition score calculating means;

utterance rejecting means for rejecting the utterance in cases where the highest recognition-desired word recognition score calculated by the recognition-desired word recognition score calculating means is equal to or lower than the highest reception word recognition score calculated by the reception word recognition score calculating means;

operation performing means for performing an operation; and

control means for controlling the operation performing means to perform the operation in cases where the uttered word received by the word receiving means is recognized as the particular recognition-desired word by the word recognizing means.

8. A speech control system according to claim 7 in which the recognition-desired words registered in the recognition-desired word registering means are classified into a group of affirmative words corresponding to affirmative expressions and a group of denial words corresponding to denial expressions, the operation performing means is an information selecting apparatus, the utter word received by the word receiving means is adopted as an affirmative opinion by the information selecting apparatus in cases where the uttered word is recognized as one affirmative word, and the utter word is adopted as a denial opinion by the information selecting apparatus in cases where the uttered word is recognized as one denial word.

9. A speech control system according to claim 7 in which the recognition-desired words registered in the recognition-desired word registering means are classified into a group of affirmative words corresponding to affirmative answers, a group of denial words corresponding to denial answers and a group of intermediate words corresponding to intermediate answers between the affirmative answers and the denial answers, the operation performing means is an automatic questionnaire apparatus, the utter word received by the word receiving means is adopted as one affirmative answer by the automatic questionnaire apparatus in cases where the uttered word is recognized as one affirmative word, and the utter word is adopted as one denial answer by the automatic questionnaire apparatus in cases where the uttered word is recognized as one denial word.

10. A speech control system according to claim 7 in which the recognition-desired words registered in the recognition-desired word registering means are classified into N groups of recognition-desired words corresponding to N operations (N is a positive integral number), and one operation is performed by the operation performing means in cases where the utter word received by the word receiving means is recognized as one recognition-desired word of one group corresponding to the operation.

11. A speech control system according to claim 7, further comprising:

rejection informing means for informing a user that the utterance received by the word receiving means is rejected in cases where the uttered word is rejected by the utterance rejecting means.