Speech recognition apparatus

• US 20020184020A1
• Filed: 03/11/2002
• Published: 12/05/2002
• Est. Priority Date: 03/13/2001
• Status: Active Grant

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Shinoda, Koichi
• Granted Patent: US 7,437,288 B2
• Time in Patent Office: Days
• US Class Current: 704/240
• CPC Class Codes: G10L 15/07 to the speaker
• CPC Class Codes: G10L 15/144 Training of HMMs

Abstract

A speech recognition apparatus using a probability model that employs a mixed distribution, the apparatus formed by a standard pattern storage means for storing a standard pattern; a recognition means for outputting recognition results corresponding to an input speech by using the standard pattern; a standard pattern generating means for inputting learning speech and generating the standard pattern; and a standard pattern adjustment means, provided between the standard pattern generating means and the standard pattern storage means, for adjusting the number of element distributions of the mixed distribution of the standard pattern.

Claims

1. A speech recognition apparatus using a probability model that employs a mixed distribution, said apparatus comprising:

a standard pattern storage means for storing a standard pattern;

a recognition means for outputting recognition results corresponding to an input speech by using said standard pattern;

a standard pattern generating means for inputting learning speech and generating said standard pattern; and

a standard pattern adjustment means, provided between said standard pattern generating means and said standard pattern storage means, for adjusting the number of element distributions of said mixed distribution of said standard pattern.

3. The speech recognition apparatus according to claim 1, wherein said standard pattern adjustment means comprising:

a tree structure generating means for generating a tree structure of an element distribution, and

an element distribution selection means for selecting a distribution response to learning data input to said standard pattern generating means.

4. The speech recognition apparatus according to claim 1, wherein said standard pattern adjustment means having a minimax distribution selection means for selecting an element distribution by using a minimax method.

5. The speech recognition apparatus according to claim 3, wherein said element distribution selection means uses an amount of learning data corresponding to each element distribution as a criterion in selection of element distributions.

6. The speech recognition apparatus according to claim 3, wherein said element distribution selection means uses a minimum description length as a criterion in selection of element distributions.

7. The speech recognition apparatus according to claim 3, wherein said element distribution selection means uses an Akaike information criterion as a criterion in selection of element distributions.

8. The speech recognition apparatus according to claim 3, wherein said tree structure generating means uses divergence as a inter-distribution distance in selection of element distributions.

9. The speech recognition apparatus according to claim 3, wherein said tree structure generating means uses a likelihood with respect to learning data as an inter-distribution distance.

10. The speech recognition apparatus according to claim 1, wherein a hidden Markov model is used as said probability model.

2. A speech recognition apparatus using a probability model that employs a mixed distribution, said apparatus comprising:

a standard pattern storage means for storing a standard pattern;

a recognition means for outputting recognition results corresponding to an input speech by using said standard pattern;

a standard pattern modification means for inputting speech for adaptation and modifying said standard pattern; and

a standard pattern adjustment means for adjusting the number of element distributions of said mixed distribution of said standard pattern.