Method for Adapting a Codebook for Speech Recognition
First Claim
1. A method for adapting a codebook for speech recognition, wherein the codebook is from a set of codebooks comprising a speaker-independent codebook and at least one speaker-dependent codebook, each codebook including a set of Gaussian densities, each Gaussian density being parameterized by a mean vector and a covariance matrix, comprising:
- (a) receiving a speech input;
(b) determining a feature vector based on the received speech input;
(c) for each of the Gaussian densities, estimating a first mean vector using an expectation process and taking into account the determined feature vector;
(d) for each of the Gaussian densities, estimating a second mean vector using an Eigenvoice adaptation and taking into account the determined feature vector; and
(e) for each of the Gaussian densities, setting its mean vector to a convex combination of the first and the second mean vector.
7 Assignments
0 Petitions
Accused Products
Abstract
A method for adapting a codebook for speech recognition, wherein the codebook is from a set of codebooks comprising a speaker-independent codebook and at least one speaker-dependent codebook is disclosed. A speech input is received and a feature vector based on the received speech input is determined. For each of the Gaussian densities, a first mean vector is estimated using an expectation process and taking into account the determined feature vector. For each of the Gaussian densities, a second mean vector using an Eigenvoice adaptation is determined taking into account the determined feature vector. For each of the Gaussian densities, the mean vector is set to a convex combination of the first and the second mean vector. Thus, this process allows for adaptation during operation and does not require a lengthy training phase.
27 Citations
27 Claims
-
1. A method for adapting a codebook for speech recognition, wherein the codebook is from a set of codebooks comprising a speaker-independent codebook and at least one speaker-dependent codebook, each codebook including a set of Gaussian densities, each Gaussian density being parameterized by a mean vector and a covariance matrix, comprising:
-
(a) receiving a speech input; (b) determining a feature vector based on the received speech input; (c) for each of the Gaussian densities, estimating a first mean vector using an expectation process and taking into account the determined feature vector; (d) for each of the Gaussian densities, estimating a second mean vector using an Eigenvoice adaptation and taking into account the determined feature vector; and (e) for each of the Gaussian densities, setting its mean vector to a convex combination of the first and the second mean vector. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. A computer program product including a tangible computer-readable medium having computer code thereon for adapting a codebook for speech recognition, wherein the codebook is from a set of codebooks comprising a speaker-independent codebook and at least one speaker-dependent codebook, each codebook a set of Gaussian densities, the computer code comprising:
-
(a) computer code for receiving a speech input; (b) computer code for determining a feature vector based on the received speech input; (c) computer code, for each of the Gaussian densities, for estimating a first mean vector using an expectation process and taking into account the determined feature vector; (d) computer code, for each of the Gaussian densities, for estimating a second mean vector using an Eigenvoice adaptation and taking into account the determined feature vector; and (e) computer code, for each of the Gaussian densities, for setting its mean vector to a convex combination of the first and the second mean vector. - View Dependent Claims (15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26)
-
-
27. An apparatus for adapting a codebook for speech recognition, wherein the codebook includes a set of Gaussian densities, the apparatus comprising:
-
a receiver for receiving a speech input; a feature vector module for determining a feature vector based on the received speech input; a first estimation module for estimating, for each of the Gaussian densities, a first mean vector using an expectation maximization process and taking into account the determined feature vector; a second estimation module for estimating, for each of the Gaussian densities, a second mean vector using an Eigenvoice adaptation and taking into account the determined feature vector; and an adapter module, for each of the Gaussian densities, setting its mean vector to a convex combination of the first and the second mean vector.
-
Specification