Detail publikace

Sequence-discriminative Training of Deep Neural Networks

Originální název

Sequence-discriminative Training of Deep Neural Networks

Anglický název

Sequence-discriminative Training of Deep Neural Networks

Jazyk

en

Originální abstrakt

This article presents experiments with DNN-HMM hybrid systems trained using frame-based cross-entropy and different sequence-discriminative criteria on the 300 hour Switchboard conversational telephone speech task.

Anglický abstrakt

This article presents experiments with DNN-HMM hybrid systems trained using frame-based cross-entropy and different sequence-discriminative criteria on the 300 hour Switchboard conversational telephone speech task.

BibTex


@inproceedings{BUT103549,
  author="Karel {Veselý} and Arnab {Ghoshal} and Lukáš {Burget} and Daniel {Povey}",
  title="Sequence-discriminative Training of Deep Neural Networks",
  annote="This article presents experiments with DNN-HMM hybrid systems trained using
frame-based cross-entropy and different sequence-discriminative criteria on the
300 hour Switchboard conversational telephone speech task.",
  address="International Speech Communication Association",
  booktitle="Proceedings of Interspeech 2013",
  chapter="103549",
  edition="NEUVEDEN",
  howpublished="print",
  institution="International Speech Communication Association",
  number="8",
  year="2013",
  month="august",
  pages="2345--2349",
  publisher="International Speech Communication Association",
  type="conference paper"
}