Speech recognition apparatus and speech recognition navigation apparatus

• US 6,708,150 B1
• Filed: 09/11/2000
• Issued: 03/16/2004
• Est. Priority Date: 09/09/1999
• Status: Active Grant

• Current Assignee: Clarion Co., Ltd. (Faurecia SA)
• Original Assignee: Zanavi Informatics Corporation
• Inventors: Kobayashi, Yoshiyuki, Hirayama, Yoshikazu
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US09/659,679
• Time in Patent Office: 1,282 Days
• Field of Search: 704/243, 704/251, 704/270, 704/255
• US Class Current: 704/243
• CPC Class Codes: G01C 21/3608 using speech input, e.g. using speech recognition
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A speech recognition apparatus includes: a speech input device; a storage device that stores a recognition word indicating a pronunciation of a word to undergo speech recognition; and a speech recognition processing device that performs speech recognition processing by comparing audio data obtained through the voice input device and speech recognition data created in correspondence to the recognition word, and the storage device stores both a first recognition word corresponding to a pronunciation of an entirety of the word to undergo speech recognition and a second recognition word corresponding to a pronunciation of only a starting portion of a predetermined length of the entirety of the word to undergo speech recognition as recognition words for the word to undergo speech recognition.

Claims

1. A speech recognition apparatus, comprising:

a voice input device;

a first storage device that stores a first recognition word indicating a pronunciation of a word to undergo speech recognition;

a second storage device that stores a specific word that includes a first pronunciation different from a second pronunciation, which specific word is prepared in advance as a word that is a common part of a plurality of words to undergo speech recognition;

a generating device that judges whether or not a given word contains the specific word as a part of the given word and generates a second recognition word of the given word by replacing a second pronunciation of the specific word with the first pronunciation of the specific word when it has been judge that the given word contains the specific;

the second pronunciation being originally included in the first recognition word of the given word;

the first pronunciation being different from the second pronunciation; and

a speech recognition processing device that performs speech recognition processing by comparing audio data obtained through the voice input device and speech recognition data created in correspondence to the second recognition word of the given word.

2. A speech recognition navigation apparatus, comprising:

a voice input device;

a first storage device that stores a first recognition word indicating a pronunciations of a word to undergo speech recognition;

a second storage device that stores a specific word that includes a first pronunciation different from a second pronunciation, which specific word is prepared in advance as a word that is a common part of a plurality of words to undergo speech recognition;

a generating device that judges whether or not a given word contains the specific word as a part of the given word and generates a second recognition word of the given word by replacing a second pronunciation of the specific word with the first pronunciation of the specific word when it has been judged that the given word contains the specific word;

the second pronunciation being originally included in the first recognition word of the given word;

the first pronunciation being different from the second pronunciation; and

a speech recognition processing device that performs speech recognition processing by comparing audio data obtained through the voice input device and speech recognition data created in correspondence to the second recognition word of the given word;

a map information storage device that stores map information; and

a control device that engages in control for providing route guidance based upon, at least, recognition results obtained by the speech recognition processing device and the map information.

3. A speech recognition navigation apparatus, comprising:

a voice input device;

a first storage device that stores a first recognition word indicating a pronunciation of a word to undergo speech recognition;

a second storage device that stores a specific word that is prepared in advance as a word that is a common part of a plurality of words to undergo speech recognition;

a generating device that judges whether or not a given word contains the specific word as a part of the given word and generates a second recognition word of the given word by adding a pronunciation of the specific word when it has been judged that the given word does not contain the specific word;

a speech recognition processing device that performs speech recognition processing by comparing audio data obtained through the voice input device and speech recognition data created in correspondence to the second recognition word of the given word;

a map information storage device that stores map information; and

a control device that engages in control for providing route guidance based upon, at least, recognition results obtained by the speech recognition processing device and the map information.

4. A method of recognition word generation through which recognition words indicating pronunciations of words to undergo speech recognition used to generate speech recognition data to be compared against audio data obtained through a voice input device are generated, the method comprising the acts of:

obtaining a first recognition word of a given word to undergo speech recognition;

obtaining a specific word that includes a first pronunciation and is prepared in advance as a word that is a common part of a plurality of words to undergo speech recognition;

judging whether or not the given word contains the specific word as a part of the given word;

generating a second recognition word of the given word by replacing a second pronunciation of the specific word with the first pronunciation of the specific word when it has been judged that the given word contains the specific word;

the second pronunciation being originally included in the first recognition word of the given word; and

the first pronunciation being different from the second pronunciation.

5. A method of recognition word generation according to claim 4, wherein:

the second pronunciation of the specific word is a standard pronunciation.

6. A method of recognition word generation according to claim 4, wherein:

the second pronunciation of the specific word is a standard pronunciation; and

the first pronunciation indicates how the specific word is pronounced in everyday life.

7. A method of recognition word generation according to claim 4, further comprising the act of:

storing both the first recognition word and the second recognition word for the given word.

8. A method of recognition word generation according to claim 4, wherein:

the first pronunciation is constituted of no sound made for the specific word.

9. A method of recognition word generation according to claim 4, wherein:

the first pronunciation of the specific word is constituted of a pronunciation corresponding to an alternative term or an abbreviated term for the specific word.

10. A recording medium that stores a recognition word generating program for generating recognition words indicating pronunciations of words to undergo speech recognition used to generate speech recognition data to be compared against audio data obtained through a voice input device in speech recognition processing, the recognition word generating program comprising:

an instruction of obtaining a first recognition word of a given word to undergo speech recognition;

an instruction of obtaining a specific word that includes a first pronunciation and is prepared in advance as a word that is a common part of a plurality of words to undergo speech recognition;

an instruction of judging whether or not the given word contains the specific word as a part of the given word;

an instruction of generating a second recognition word of the given word by replacing a second pronunciation of the specific word with the first pronunciation of the specific word when it has been judged that the given word contains the specific word;

the second pronunciation being originally included in the first recognition word of the given word; and

the first pronunciation being different from the second pronunciation.

11. A data signal transmitted in a communication line that comprises a recognition word generating program for generating recognition words indicating pronunciations of words to undergo speech recognition used to generate speech recognition data to be compared against audio data obtained through a voice input device in speech recognition processing, the recognition word generating program comprising:

an instruction of obtaining a first recognition word of a given word to undergo speech recognition;

an instruction of obtaining a specific word that includes a first pronunciation and is prepared in advance as a word that is a common part of a plurality of words to undergo speech recognition;

an instruction of judging whether or not the given word contains the specific word as a part of the given word;

an instruction of generating a second recognition word of the given word by replacing a second pronunciation of the specific word with the first pronunciation of the specific word when it has been judged that the given word contains the specific word;

the second pronunciation being originally included in the first recognition word of the given word; and

the first pronunciation being different from the second pronunciation.

12. A method of recognition word generation through which recognition words indicating pronunciations of words to undergo speech recognition used to generate speech recognition data to be compared against audio data obtained through a voice input device are generated, the method comprising the acts of:

obtaining a first recognition word of a given word to undergo speech recognition in a given category;

obtaining a specific word that is prepared in advance as a word that is a common part of a plurality of words to undergo speech recognition in the given category;

judging whether or not the given word contains the specific word as a part of the given word;

generating a second recognition word of the given word by adding a pronunciation of the specific word when it has been judged that the given word does not contain the specific word.

13. A speech recognition apparatus, comprising:

a voice input device;

a first storage device that stores a first recognition word indicating a pronunciation of a word to undergo speech recognition;

a second storage device that stores a specific word that is prepared in advance as a word that is a common part of a plurality of words to undergo speech recognition;

a generating device that judges whether or not a given word contains the specific word as a part of the given word and generates a second recognition word of the given word by adding a pronunciation of the specific word when it has been judged that the given word does not contain the specific word and;

a speech recognition processing device that performs speech recognition processing by comparing audio data obtained through the voice input device and speech recognition data created in correspondence to the second recognition word of the given word.