Sequence-discriminative training of deep neural networks

@inproceedings{Vesel2013SequencediscriminativeTO,
  title={Sequence-discriminative training of deep neural networks},
  author={Karel Vesel{\'y} and Arnab Ghoshal and Luk{\'a}s Burget and Daniel Povey},
  booktitle={INTERSPEECH},
  year={2013}
}
Sequence-discriminative training of deep neural networks (DNNs) is investigated on a 300 hour American English conversational telephone speech task. Different sequencediscriminative criteria — maximum mutual information (MMI), minimum phone error (MPE), state-level minimum Bayes risk (sMBR), and boosted MMI — are compared. Two different heuristics are investigated to improve the performance of the DNNs trained using sequence-based criteria — lattices are regenerated after the first iteration of… CONTINUE READING
Highly Influential
This paper has highly influenced 35 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 570 citations. REVIEW CITATIONS

6 Figures & Tables

Topics

Statistics

05010015020112012201320142015201620172018
Citations per Year

570 Citations

Semantic Scholar estimates that this publication has 570 citations based on the available data.

See our FAQ for additional information.