Discriminative clustering methods for automatic speech recognition
First Claim
Patent Images
1. A discriminative clustering method for automatic speech recognition, comprising:
- providing a set of Gaussian distributions corresponding an acoustic vector space;
testing said distributions to identify selected distributions having a predetermined proximity to one another based on a distance measure and merging said selected distributions into at least one new distribution;
computing the centroid of said new distribution by minimizing the Bhattacharyya distance between selected distribution and its centroid.
4 Assignments
0 Petitions
Accused Products
Abstract
The discriminative clustering technique tests a provided set of Gaussian distributions corresponding to an acoustic vector space. A distance metric, such as the Bhattacharyya distance, is used to assess which distributions are sufficiently proximal to be merged into a new distribution. Merging is accomplished by computing the centroid of the new distribution by minimizing the Bhattacharyya distance between the parameters of the Gaussian distributions being merged.
75 Citations
13 Claims
-
1. A discriminative clustering method for automatic speech recognition, comprising:
-
providing a set of Gaussian distributions corresponding an acoustic vector space;
testing said distributions to identify selected distributions having a predetermined proximity to one another based on a distance measure and merging said selected distributions into at least one new distribution;
computing the centroid of said new distribution by minimizing the Bhattacharyya distance between selected distribution and its centroid. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A method for automatic speech recognition, comprising:
-
providing a set of Gaussian distributions corresponding an acoustic vector space;
a step for testing said distributions to identify selected distributions;
a step for merging said selected distributions into at least one new distribution; and
a step for computing the centroid of said new distribution. - View Dependent Claims (8, 9)
-
-
10. A discriminative clustering method for automatic speech recognition, comprising:
-
providing a set of Gaussian distributions corresponding an acoustic vector space;
computing a Bhattacharyya distance measure between each of said distributions;
selecting distributions having a predetermined proximity to one another based on a distance measure; and
merging said selected distributions into at least one new distribution. - View Dependent Claims (11, 12, 13)
where μ
2 and μ
2 are the mean vectors associated with distributions g1 and g2 and Σ
1 and Σ
2 are the respective covariance matrices.
-
-
12. The method of claim 10 further comprising:
computing a centroid for said new distribution by minimizing the Bhattacharyya distance between said selected distributions.
-
13. The method of claim 10 wherein the centroid of the new distribution which contains Gaussian distributions gi with a weight of wi, i=1, . . . , N is computed in accordance with
-
c = ∑ i w i * ( σ c 2 + σ i 2 ) - 1 * μ i ∑ i w i * ( σ c 2 + σ i 2 ) - 1 where σ
2 is the variance and μ
is the mean associated with a specific component of the feature vector.
-
Specification