Name
Abstract | ||
|---|---|---|
The Discriminative Feature Extraction (DFE) method provides an appropriate formalism for the design of the front-end feature extraction module in pattern classification systems. In the recent years, this formalism has been successfully applied to different speech recognition problems, like classification of vowels, classification of phonemes or isolated word recognition. The DFE formalism can be applied to weight the contribution of the components in the feature vector. This variant of DFE, that we call Discriminative Feature Weighting (DFW), improves the pattern classification systems by enhancing those components more relevant for the discrimination among the different classes. This paper is dedicated to the application of the DFW formalism to Continuous Speech Recognizers (CSR) based on Hidden Markov Models (HMMs). Two different types of HMM-based speech recognizers are considered: recognizers based on Discrete-HMMs (DHMMs) (for which the acoustic evaluation is based on an Euclidean distance measure) and Semi-Continuous-HMMs (SCHMMs) (for which the acoustic evaluation is performed making use of a mixture of multivariated Gaussians). We report how the components can be weighted and how the weights can be discriminatively trained and applied to the speech recognizers. We present recognition results for several continuous speech recognition tasks. The experimental results show the utility of DFW for HMM-based continuous speech recognizers. |
Year | DOI | Venue |
|---|---|---|
2002 | 10.1016/S0167-6393(01)00068-1 | Speech Communication |
Keywords | Field | DocType |
discriminative feature weighting,cost function,appropriate formalism,partial probability weighting,continuous speech recognition,discriminative weighting by transformation,minimum classification error,hmm-based continuous speech recognizers,probability density function,pattern classification system,acoustic evaluation,error-rate,dfe formalism,dfw formalism,speech recognizers,different speech recognition problem,hidden markov model,continuous speech recognition task,discriminative feature extraction,hmm-based speech recognizers,feature vector,front end,euclidean distance,error rate,word recognition,feature extraction,speech recognition | Feature vector,Weighting,Pattern recognition,Computer science,Word error rate,Word recognition,Feature extraction,Speech recognition,Artificial intelligence,Hidden Markov model,Discriminative model,Probability density function | Journal |
Volume | Issue | ISSN |
38 | 3-4 | Speech Communication |
Citations | PageRank | References |
9 | 0.83 | 29 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ángel de la Torre | 1 | 482 | 34.91 |
| Antonio M. Peinado | 2 | 376 | 41.97 |
| Antonio J. Rubio | 3 | 466 | 36.14 |
| José C. Segura | 4 | 481 | 38.14 |
| Carmen Benı́tez | 5 | 154 | 7.67 |