Source normalization training for HMM modeling of speech

• US 6,980,952 B1
• Filed: 06/07/2000
• Issued: 12/27/2005
• Est. Priority Date: 08/15/1998
• Status: Expired due to Term

• Current Assignee: Intel Corporation
• Original Assignee: Texas Instruments, Inc.
• Inventors: Gong, Yifan
• Primary Examiner(s): Azad, Abul K.
• Application Number:
  US09/589,252
• Time in Patent Office: 2,029 Days
• Field of Search: 704/233, 704/234, 704/243, 704/244, 704/245, 704/255, 704/240
• US Class Current: 704/234
• CPC Class Codes: G10L 15/144 Training of HMMs

Abstract

A maximum likelihood (ML) linear regression (LR) solution to environment normalization is provided where the environment is modeled as a hidden (non-observable) variable. By application of an expectation maximization algorithm and extension of Baum-Welch forward and backward variables (Steps 23a–23d) a source normalization is achieved such that it is not necessary to label a database in terms of environment such as speaker identity, channel, microphone and noise type.

Claims

1. An improved speech recognition system comprising:

a speech recognizer; and

a source normalization model coupled to said recognizer for recognizing incoming speech;

said model derived by a method of source normalization training for HMM modeling comprising the steps of;

a) providing an initial speech recognition model and

b) performing on said initial speech recognition model the following steps to get a new speech recognition model;

b₁) estimation of intermediate quantities;

b₂) performing re-estimation to determine probabilities;

b₃) deriving mean vector and bias vector; and

b₄) solving jointly for mean vector and bias vector.

2. The recognizer of claim 1 including the step b₅) of replacing old speech recognition model for the calculated ones and step c) determining after a new speech recognition model is formed if it differs significantly from the previous speech recognition model and if so repeating the steps b₁–

b₅.

3. The recognizer of claim 1 wherein said step b₂ includes one or more of performing re-estimation to determine initial state probability, transition probability, mixture component probability and environment probability.

4. The recognizer of claim 1 wherein said step b₄ includes solving jointly for mean vector and bias vector using linear equations and determining variances and transformations.

5. The recognizer of claim 1 wherein said step b₂ includes performing re-estimation to determine initial state probability, transition probability, mixture component probability and environment probability.

6. The recognizer of claim 5 wherein said step b₄ includes solving jointly for mean vector and bias vector using linear equations and determining variances and transformations.

7. The recognizer of claim 6 including the steps of replacing old speech recognition model for the calculated ones and determining after a new speech recognition model is formed if it differs significantly from the previous model and if so repeating the steps b1–

b5.

8. A method of source normalization for modeling of speech comprising the steps of:

a) providing an initial speech recognition model and

b) performing on said initial speech recognition model the following steps to get a new speech recognition model;

b₁) estimation of intermediate quantities;

b₂) performing re-estimation to determine probabilities;

b₃) deriving mean vector and bias vector; and

b₄) solving jointly for mean vector and bias vector.

9. The method of claim 8 including the step b₅) of replacing old speech recognition model for the calculated ones and step c) determining after a new speech recognition model is formed if it differs significantly from the previous speech recognition model and if so repeating the steps b₁–

b₅.

10. The method of claim 8 wherein said step b₂ includes one or more of performing re-estimation to determine initial state probability, transition probability, mixture component probability and environment probability.

11. The method of claim 8 wherein said step b₄ includes solving jointly for mean vector and bias vector using linear equations and determining variances and transformations.

12. The method of claim 8 wherein said step b₂ includes performing re-estimation to determine initial state probability, transition probability, mixture component probability and environment probability.

13. The Method of claim 12 wherein said step b₄ includes solving jointly for mean vector and bias vector using linear equations and determining variances and transformations.

14. The method of claim 13 including the step b₅) of replacing old speech recognition model for the calculated ones and step c) determining after a new speech recognition model is formed if it differs significantly from the previous speech recognition model and if so repeating the steps b1–

b5.