US5963906A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Speech recognition training
Assignee: AT&T Inc
•
Filing: 1997-05-20
•
Granted: 1999-10-05
•
Expires: 2017-05-20
Abstract
Abstract A method and system performs speech recognition training using Hidden Markov Models. Initially, preprocessed speech signals that include a plurality of observations are stored by the system. Initial Hidden Markov Model (HMM) parameters are then assigned. Summations are then calculated using modified equations derived substantially from the following equations, wherein u≦v<w: P(X.sub.u.sup.v)=P(x.sub.u.sup.v)P(x.sub.v+1.sup.w) and Ω.sub.ij (x.sub.u.sup.w)=Ω.sub.ij (x u v )P(x v+1 w )+P(x u v )Ω ij (x v+1 w ) The calculated summations are then used to perform HMM parameter reestimation. It then determines whether the HMM parameters have converged. If they have, the HMM parameters are then stored. However, if the HMM parameters have not converged, the system again calculates summations, performs HMM parameter reestimation using the summations, and determines whether the parameters have converged. This process is repeated iteratively until the HMM parameters have converged.
Inventors
- 👤 William Turin
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 22:38
CPC Classifications
G; G10; G10L; G10L15/00; G10L15/08; G10L15/14; G10L15/142; G10L15/144
Claims Analysis
Total Claims: 10
Claim 1
Independent Claim
121 words
In a method of performing speech recognition training using Hidden Markov Models comprising the steps of storing preprocessed speech signals that include a plurality of observations, assigning initial model parameters, performing model reestimation using the Baum-Welch algorithm, and storing the model parameters if they have converged, wherein the improvement comprises: partitioning the stored speech signals into at least a first and second set of training data; calculating a first summation using the first set of training data; calculating a second summation using the second set of training data; calculating a final summation using the first and second summations; and using said final summation in the model reestimation step, wherein the first summation and the second summation are calculated on parallel processors.
Claim 2
Dependent Claim
121 words
In a method of performing speech recognition training using Hidden Markov Models comprising the steps of storing preprocessed speech signals that include a plurality of observations, assigning initial model parameters, performing model reestimation using the Baum-Welch algorithm, and storing the model parameters if they have converged, wherein the improvement comprises: partitioning the stored speech signals into at least a first and second set of training data; calculating a first summation using the first set of training data; calculating a second summation using the second set of training data; calculating a final summation using the first and second summations; and using said final summation in the model reestimation step, wherein the first summation and the second summation are calculated on parallel processors.
Claim 3
Dependent Claim
14 words
The method of claim 1 wherein the final summation is calculated recursively in parallel.
Claim 4
Dependent Claim
16 words
The method of claim 1 wherein the final summation is calculated recursively in a forward-only direction.
Claim 5
Dependent Claim
16 words
The method of claim 3 wherein the final summation is calculated recursively in a backward-only direction.
Claim 6
Dependent Claim
139 words
In a system for performing speech recognition training using Hidden Markov Models comprising means for storing preprocessed speech signals that include a plurality of observations, means for assigning initial model parameters, means for performing model reestimation using the Baum-Welch algorithm, and means for storing the model parameters if they have converged, wherein the improvement comprises: means for partitioning the stored speech signals into at least a first and second set of training data; means for calculating a first summation using the first set of training data, the means further comprising a first processor; means for calculating a second summation using the second set of training data, the means further comprising a second processor; means for calculating a final summation using the first and second summations; and means for providing the final summation to the means for performing model reestimation.
Claim 7
Dependent Claim
139 words
In a system for performing speech recognition training using Hidden Markov Models comprising means for storing preprocessed speech signals that include a plurality of observations, means for assigning initial model parameters, means for performing model reestimation using the Baum-Welch algorithm, and means for storing the model parameters if they have converged, wherein the improvement comprises: means for partitioning the stored speech signals into at least a first and second set of training data; means for calculating a first summation using the first set of training data, the means further comprising a first processor; means for calculating a second summation using the second set of training data, the means further comprising a second processor; means for calculating a final summation using the first and second summations; and means for providing the final summation to the means for performing model reestimation.
Claim 8
Dependent Claim
17 words
The system of claim 5 wherein the means for calculating a final summation uses a parallel recursion.
Claim 9
Dependent Claim
17 words
The system of claim 5 wherein the means for calculating a final summation uses a forward-only recursion.
Claim 10
Dependent Claim
17 words
The system of claim 5 wherein the means for calculating a final summation uses a backward-only recursion.
References Cited (Backward Citations)
US5381513A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2002-10-04 | 2003-04-05 | 2003-10-05 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2006-10-04 | 2007-04-05 | 2007-10-05 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2010-10-04 | 2011-04-05 | 2011-10-05 | $7700.00 | Window Closed / Lapsed |