The Lincoln tied-mixture HMM continuous speech recognizer
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
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
Foreground auditory scene analysis for hearing aids
Pattern Recognition Letters
Efficient codebooks for fast and accurate low resource ASR systems
Speech Communication
Gaussian selection using self-organizing map for automatic speech recognition
WSOM'11 Proceedings of the 8th international conference on Advances in self-organizing maps
Trends and advances in speech recognition
IBM Journal of Research and Development
Real-time incremental speech-to-speech translation of dialogs
NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Fast Likelihood Computation in Speech Recognition using Matrices
Journal of Signal Processing Systems
Hi-index | 0.00 |
In speech recognition systems based on Continuous Observation Density Hidden Markov Models, the computation of the state likelihoods is an intensive task. This paper presents an efficient method for the computation of the likelihoods defined by weighted sums (mixtures) of Gaussians. The proposed method uses vector quantization of the input feature vector to identify a subset of Gaussian neighbors. It is here shown that, under certain conditions, instead of computing the likelihoods of all the Gaussians, one needs to compute the likelihoods of only the Gaussian neighbors. Significant (up to a factor of nine) likelihood computation reductions have been obtained on various data bases, with only a small loss of recognition accuracy.