Speech Recognition
First Claim
1. A processor implemented method for speech recognition of a speech signal comprising:
- within a processor;
providing at least one codebook comprising codebook entries, in particular, multivariate Gaussians of feature vectors, that are frequency weighted; and
processing the speech signal for speech recognition comprising;
extracting at least one feature vector from the speech signal and matching the feature vector with the entries of the codebook.
2 Assignments
0 Petitions
Accused Products
Abstract
The present invention relates to a method for speech recognition of a speech signal comprising the steps of providing at least one codebook comprising codebook entries, in particular, multivariate Gaussians of feature vectors, that are frequency weighted such that higher weights are assigned to entries corresponding to frequencies below a predetermined level than to entries corresponding to frequencies above the predetermined level and processing the speech signal for speech recognition comprising extracting at least one feature vector from the speech signal and matching the feature vector with the entries of the codebook.
-
Citations
24 Claims
-
1. A processor implemented method for speech recognition of a speech signal comprising:
-
within a processor; providing at least one codebook comprising codebook entries, in particular, multivariate Gaussians of feature vectors, that are frequency weighted; and processing the speech signal for speech recognition comprising; extracting at least one feature vector from the speech signal and matching the feature vector with the entries of the codebook. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A processor implemented method for retrofitting a speech recognition system that comprises at least one first code-book having codebook entries, in particular, multivariate Gaussians, the method comprising:
-
in a processor; weighting the entries of the at least one first codebook such that higher weights are assigned to entries corresponding to frequencies below a predetermined level than to entries corresponding to frequencies above the predetermined level; and generating at least one second codebook to be used for speech recognition by the speech recognition means by storing the weighted entries of the at least one first codebook. - View Dependent Claims (9)
-
-
10. A computer program product comprising a computer readable medium having computer-executable instructions thereon for speech recognition of a speech signal comprising, the computer-executable instructions comprising:
-
computer code for providing at least one codebook comprising codebook entries, in particular, multivariate Gaussians of feature vectors, that are frequency weighted; and computer code for processing the speech signal for speech recognition comprising; computer code for extracting at least one feature vector from the speech signal and computer code for matching the feature vector with the entries of the codebook. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17, 23)
-
-
18. A computer program product comprising a computer readable medium having computer executable code thereon for retrofitting a speech recognition system that comprises at least one first code-book having codebook entries that include multivariate Gaussians, the computer executable code comprising:
-
computer code for weighting the entries of the at least one first codebook such that higher weights are assigned to entries corresponding to frequencies below a predetermined level than to entries corresponding to frequencies above the predetermined level; and computer code for generating at least one second codebook to be used for speech recognition by the speech recognition means by storing the weighted entries of the at least one first codebook. - View Dependent Claims (19)
-
-
20. A Speech recognition system, comprising:
-
a speech processing engine for receiving a speech signal; memory containing; at least one codebook comprising multivariate Gaussians; wherein the multivariate Gaussians are weighted such that higher weights are assigned to entries corresponding to frequencies below a predetermined level than to entries corresponding to frequencies above the predetermined level and wherein the codebook is used by the speech processing engine to determine words within the speech signal. - View Dependent Claims (21, 22, 24)
-
Specification