Speech recognition apparatus and speech recognition method

• US 20060100876A1
• Filed: 12/08/2005
• Published: 05/11/2006
• Est. Priority Date: 06/08/2004
• Status: Active Grant

• Current Assignee: Panasonic Intellectual Property Corporation of America (Panasonic Holdings Corporation)
• Original Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Inventors: Nishizaki, Makoto, Yoshizawa, Shinichi, Nakatoh, Yoshihisa, Yamada, Maki
• Granted Patent: US 7,310,601 B2
• Time in Patent Office: Days
• US Class Current: 704/257
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems

Abstract

To provide a speech recognition apparatus which appropriately performs speech recognition by generating, in real time, language models adapted to a new topic even in the case where topics are changed. The speech recognition apparatus includes: a word specification unit for obtaining and specifying a word; a language model information storage unit for storing language models for recognizing speech and the respectively corresponding pieces of tag information; a combination coefficient calculation unit for calculating the weights of the respective language models, as combination coefficients, according to the word obtained by the word specification unit, based on the relevance degree between the word obtained by the word specification unit and the tag information of each language model; a language probability calculation unit for calculating the probabilities of word appearance by combining the respective language models according to the calculated combination coefficients; and a speech recognition unit for recognizing speech using the calculated probabilities of word appearance.

Claims

1. A speech recognition apparatus which obtains and recognizes speech, said apparatus comprising:

a language model storage unit operable to store language models for recognizing speech;

a tag information storage unit operable to store a piece of tag information for each of the language models, the tag information indicating a feature of each language model;

a relevance degree holding unit operable to hold a relevance degree between each piece of tag information and each of words;

an importance degree holding unit operable to hold an importance degree of each piece of tag information to a corresponding one of the language models;

a word obtainment unit operable to obtain one of the words;

a relevance degree derivation unit operable to derive the relevance degree between each piece of tag information and the word obtained by said word obtainment unit, from the respective relevance degrees held by said relevance degree holding unit;

a combination coefficient calculation unit operable to calculate, as a combination coefficient, a weight of each language model which corresponds to the obtained word, based on the relevance degrees derived by said relevance degree derivation unit and the importance degrees held by said importance degree holding unit, each of the relevance degrees indicating a relevance degree between the obtained word and one of the pieces of tag information of each language model;

a probability calculation unit operable to calculate a probability of appearance of a predetermined word using, in combination, a specific model probability and a combination coefficient, the specific model probability being derived for each of the language models and indicating the probability that the predetermined word will appear in the speech, and the combination coefficient for each of the language models being calculated by said combination coefficient calculation unit; and

a recognition unit operable to recognize the speech using the probability calculated by said probability calculation unit,

wherein said word obtainment unit is operable to obtain the one of the words adapted to the speech recognized by said recognition unit.

2. The speech recognition apparatus according to claim 1,

wherein said combination coefficient calculation unit is operable to calculate a combination coefficient of each language model, each time a word is obtained by said word obtainment unit.

3. The speech recognition apparatus according to claim 1,

wherein said combination coefficient calculation unit is operable to calculate a combination coefficient of each language model, each time plural words are obtained by said word obtainment unit.

4. The speech recognition apparatus according to claim 1,

wherein said combination coefficient calculation unit is operable to calculate a weight, as a combination coefficient, of each language model corresponding to the plural words, based on the relevance degree between the plural words obtained by said word obtainment unit and the tag information of each language model.

5. The speech recognition apparatus according to claim 1, further comprising

a keyword extraction unit operable to extract a keyword from at least one of an electronic data that a user is browsing and profile information related to the user,

wherein said word obtainment unit is operable to obtain, as the obtained one of the words, the keyword extracted by said keyword extraction unit.

6. A speech recognition method for obtaining speech and recognizing the data stored in a recording medium,

wherein the recording medium includes:

a language model storage unit operable to store language models for recognizing speech;

a tag information storage unit operable to store a piece of tag information for each of the language models, the tag information indicating a feature of each language model;

a relevance degree holding unit operable to hold a relevance degree between each piece of tag information and each of words; and

an importance degree holding unit operable to hold an importance degree of each piece of tag information to a corresponding one of the language models,

said speech recognition method comprises;

obtainment of one of the words;

derivation of the relevance degree between each piece of tag information and the word obtained by said obtainment of the word, from the respective relevance degrees held by the relevance degree holding unit;

calculation of, as a combination coefficient, a weight of each language model which corresponds to the obtained word, based on the relevance degrees derived by said derivation of the relevance degrees and the importance degrees held by the importance degree holding unit, each of the relevance degrees indicating a relevance degree between the obtained word and one of the pieces of tag information of each language model;

calculation of a probability of appearance of a predetermined word using, in combination, a specific model probability and a combination coefficient, the specific model probability being derived for each of the language models and indicating the probability that the predetermined word will appear in the speech, and the combination coefficient for each of the language models being calculated in said calculation of the combination coefficient;

recognition of the speech using the probability calculated in said calculation of the probability,

wherein, said obtainment of the word includes obtainment of the one of the words adapted to the speech recognized in said recognition of the speech.

7. A program causing a computer to obtain speech and recognize the speech using the data stored on a recording medium,

wherein the recording medium includes:

a language model storage unit operable to store language models for recognizing speech;

a tag information storage unit operable to store a piece of tag information for each of the language models, the tag information indicating a feature of each language model;

a relevance degree holding unit operable to hold a relevance degree between each piece of tag information and each of words; and

an importance degree holding unit operable to hold an importance degree of each piece of tag information to a corresponding one of the language models,

said program causes a computer to execute;

obtainment of one of the words;

derivation of the relevance degree between each piece of tag information and the word obtained by said obtainment of the word, from the respective relevance degrees held by the relevance degree holding unit;

calculation of, as a combination coefficient, a weight of each language model which corresponds to the obtained word, based on the relevance degrees derived by said derivation of the relevance degrees and the importance degrees held by the importance degree holding unit, each of the relevance degrees indicating a relevance degree between the obtained word and one of the pieces of tag information of each language model;

calculation of a probability of appearance of a predetermined word using, in combination, a specific model probability and a combination coefficient, the specific model probability being derived for each of the language models and indicating the probability that the predetermined word will appear in the speech, and the combination coefficient for each of the language models being calculated in said calculation of the combination coefficient;

recognition of the speech using the probability calculated in said calculation of the probability,

wherein, said obtainment of the word includes obtainment of the one of the words adapted to the speech recognized in said recognition of the speech.