Sequence-discriminative training of deep neural networks
Brno University of Technology · University of Edinburgh · +1 more institution
Abstract
Sequence-discriminative training of deep neural networks (DNNs) is investigated on a 300 hour American English conversational telephone speech task. Different sequence-discriminative criteria ndash;- maximum mutual information (MMI), minimum phone error (MPE), state-level minimum Bayes risk (sMBR), and boosted MMI ndash;- are compared. Two different heuristics are investigated to improve the performance of the DNNs trained using sequence-based criteria ndash;- lattices are re-generated after the first iteration of training; and, for MMI and BMMI, the frames where the numerator and denominator hypotheses are disjoint are removed from the gradient computation. Starting from a competitive DNN baseline trained…
Citation impact
- FWCI
- 130.95
- Percentile
- 100%
- References
- 27
Authors
4Topics & keywords
- Discriminative model
- Training (meteorology)
- Artificial intelligence
- Computer science
- Sequence (biology)
- Artificial neural network
- Pattern recognition (psychology)
- Speech recognition
- Reduced inequalities