Improvements in connected digit recognition using higher order spectral and energy features
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
A new connected word recognition algorithm based on HMM/LVQ segmentation and LVQ classification
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Segmental GPD training of HMM based speech recognizer
ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
Discriminative analysis for feature reduction in automatic speech recognition
ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
Speech recognition using segmental neural nets
ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
Direct posterior confidence for out-of-vocabulary spoken term detection
ACM Transactions on Information Systems (TOIS)
| Hi-index | 0.00 |
A classifier for utterance rejection in a Hidden Markov Model (HMM) based speech recognizer is presented. This classifier, termed the two pass classifier, is a post processor to the HMM recognizer, and consists of a two stage discriminant analysis. The first stage employs the Generalized Probabilistic Descent (GPD) discriminative training framework, while the second stage performs linear discrimination combining the output of the first stage with the HMM likelihood scores. In this fashion the classification power of the HMM is combined with that of the GPD stage which is specifically designed for keyword/non-keyword classification. Experimental results show that, on two separate databases, the two pass classifier significantly outperforms a single pass classifier based solely on the HMM likelihood scores.