Publication result detail

Sequence-discriminative Training of Deep Neural Networks

VESELÝ, K.; GHOSHAL, A.; BURGET, L.; POVEY, D.

Original Title

Sequence-discriminative Training of Deep Neural Networks

English Title

Sequence-discriminative Training of Deep Neural Networks

Type

Paper in proceedings outside WoS and Scopus

Original Abstract

This article presents experiments with DNN-HMM hybrid systemstrained using frame-based cross-entropy and differentsequence-discriminative criteria on the 300 hour Switchboardconversational telephone speech task.

English abstract

This article presents experiments with DNN-HMM hybrid systemstrained using frame-based cross-entropy and differentsequence-discriminative criteria on the 300 hour Switchboardconversational telephone speech task.

Keywords

speech recognition, deep learning, sequencecriteriontraining, neural networks, reproducible research

Key words in English

speech recognition, deep learning, sequencecriteriontraining, neural networks, reproducible research

Authors

VESELÝ, K.; GHOSHAL, A.; BURGET, L.; POVEY, D.

RIV year

2014

Released

25.08.2013

Publisher

International Speech Communication Association

Location

Lyon

ISBN

978-1-62993-443-3

Book

Proceedings of Interspeech 2013

ISBN

2308-457X

Periodical

Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013).

Number

8

State

French Republic

Pages from

2345

Pages to

2349

Pages count

5

URL

http://www.fit.vutbr.cz/research/groups/speech/publi/2013/vesely_interspeech2013_IS131333.pdf

BibTex

@inproceedings{BUT103549,
  author="Karel {Veselý} and Arnab {Ghoshal} and Lukáš {Burget} and Daniel {Povey}",
  title="Sequence-discriminative Training of Deep Neural Networks",
  booktitle="Proceedings of Interspeech 2013",
  year="2013",
  journal="Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013).",
  number="8",
  pages="2345--2349",
  publisher="International Speech Communication Association",
  address="Lyon",
  isbn="978-1-62993-443-3",
  issn="2308-457X",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2013/vesely_interspeech2013_IS131333.pdf"
}