Introduction to statistical pattern recognition (2nd ed.)
Introduction to statistical pattern recognition (2nd ed.)
Fundamentals of speech recognition
Fundamentals of speech recognition
Multiple VQ hidden Markov modelling for speech recognition
Speech Communication
Speech Communication - Special issue on acoustic echo control and speech enhancement techniques
Cepstrum-Based Filter-Bank Design Using Discriminative Feature Extraction Training at Various Levels
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2
Pattern recognition using discriminative feature extraction
IEEE Transactions on Signal Processing
Discriminative metric design for robust pattern recognition
IEEE Transactions on Signal Processing
Weighted instance-based learning using representative intervals
MICAI'07 Proceedings of the artificial intelligence 6th Mexican international conference on Advances in artificial intelligence
Hi-index | 0.00 |
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.