Fast update implementation for efficient latent semantic language modeling
First Claim
1. A method for performing speech recognition comprising:
- receiving speech signals;
processing the received speech signals directly using a language model produced by integrating a latent semantic analysis language model into an n-gram probability language model, wherein the latent semantic analysis language model probability is computed using a first pseudo-document vector derived from a second pseudo-document vector, the first and second pseudo-document vectors representing pseudo-documents created from the received speech signals at different points in time; and
generating a linguistic message representative of the received speech signals.
2 Assignments
0 Petitions
Accused Products
Abstract
Speech or acoustic signals are processed directly using a hybrid stochastic language model produced by integrating a latent semantic analysis language model into an n-gram probability language model. The latent semantic analysis language model probability is computed using a first pseudo-document vector that is derived from a second pseudo-document vector with the pseudo-document vectors representing pseudo-documents created from the signals received at different times. The first pseudo-document vector is derived from the second pseudo-document vector by updating the second pseudo-document vector directly in latent semantic analysis space in response to at least one addition of a candidate word of the received speech signals to the pseudo-document represented by the second pseudo-document vector. Updating precludes mapping a sparse representation for a pseudo-document into the latent semantic space to produce the first pseudo-document vector. A linguistic message representative of the received speech signals is generated.
-
Citations
24 Claims
-
1. A method for performing speech recognition comprising:
-
receiving speech signals;
processing the received speech signals directly using a language model produced by integrating a latent semantic analysis language model into an n-gram probability language model, wherein the latent semantic analysis language model probability is computed using a first pseudo-document vector derived from a second pseudo-document vector, the first and second pseudo-document vectors representing pseudo-documents created from the received speech signals at different points in time; and
generating a linguistic message representative of the received speech signals. - View Dependent Claims (2, 3, 4, 5, 6)
constructing a sparse representation for a current word;
mapping the sparse representation for the current word to a vector for the current word; and
evaluating the closeness between the vector for the current word and the first pseudo-document vector.
-
-
5. The method of claim 4, wherein the mapping follows from a singular value decomposition of a matrix of co-occurrences between at least one word and at least one document.
-
6. The method of claim 2, wherein updating precludes mapping a sparse representation for a pseudo-document into the latent semantic analysis space to produce the first pseudo-document vector, wherein a number of computations of the processing are reduced by a value approximately equal to a vocabulary size.
- 7. A method for generating a language model for use in a speech recognition system, the method comprising integrating a latent semantic analysis language model into an n-gram probability language model, wherein the latent semantic analysis language model probability is computed using a first pseudo-document vector derived from a second pseudo-document vector, the first and second pseudo-document vectors representing pseudo-documents created from the received speech signals at different points in time.
- 10. A speech recognition process comprising a statistical learning technique that uses a language model, the language model produced by integrating a latent semantic analysis language model into an n-gram probability language model, wherein the latent semantic analysis language model probability is computed using a first pseudo-document vector derived from a second pseudo-document vector, the first and second pseudo-document vectors representing pseudo-documents created from the received speech signals at different points in time.
-
13. An apparatus for speech recognition comprising:
-
at least one processor;
an input coupled to the at least one processor, the input capable of receiving speech signals, the at least one processor configured to recognize the received speech signals using a language model produced by integrating a latent semantic analysis language model into an n-gram probability language model, wherein the latent semantic analysis language model probability is computed using a first pseudo-document vector derived from a second pseudo-document vector, the first and second pseudo-document vectors representing pseudo-documents created from the received speech signals at different points in time; and
an output coupled to the at least one processor, the output capable of providing a linguistic message representative of the received speech signals. - View Dependent Claims (14, 15, 16, 17, 18)
constructing a sparse representation for a current word;
mapping the sparse representation for the current word to a vector for the current word; and
evaluating the closeness between the vector for the current word and the first pseudo-document vector.
-
-
17. The apparatus of claim 16, wherein the mapping follows from a singular value decomposition of a matrix of co-occurrences between at least one word and at least one document.
-
18. The apparatus of claim 14, wherein updating precludes mapping a sparse representation for a pseudo-document into the latent semantic analysis space to produce the first pseudo-document vector, wherein a number of computations of the processing are reduced by a value approximately equal to a vocabulary size.
-
19. A computer readable medium containing executable instructions which, when executed in a processing system, causes the system to perform a method for recognizing speech, the method comprising:
-
receiving speech signals;
processing the received speech signals directly using a language model produced by integrating a latent semantic analysis language model into an n-gram probability language model, wherein the latent semantic analysis language model probability is computed using a first pseudo-document vector derived from a second pseudo-document vector, the first and second pseudo-document vectors representing pseudo-documents created from the received speech signals at different points in time; and
generating a linguistic message representative of the received speech signals. - View Dependent Claims (20, 21, 22, 23, 24)
constructing a sparse representation for a current word;
mapping the sparse representation for the current word to a vector for the current word; and
evaluating the closeness between the vector for the current word and the first pseudo-document vector.
-
-
23. The computer readable medium of claim 22, wherein the mapping follows from a singular value decomposition of a matrix of co-occurrences between at least one word and at least one document.
-
24. The computer readable medium of claim 20, wherein updating precludes mapping a sparse representation for a pseudo-document into the latent semantic analysis space to produce the first pseudo-document vector, wherein a number of computations of the processing are reduced by a value approximately equal to a vocabulary size.
Specification