Publication detail

Improved Feature Processing for Deep Neural Networks

RATH, S. POVEY, D. VESELÝ, K. ČERNOCKÝ, J.

Original Title

Improved Feature Processing for Deep Neural Networks

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

In this paper, we explore various methods of providing higherdimensional features to DNNs, while still applying speaker adaptation with fMLLR of low dimensionality.

Keywords

speech recognition, speaker recognition, neural networks, speaker adaptation

Authors

RATH, S.; POVEY, D.; VESELÝ, K.; ČERNOCKÝ, J.

RIV year

2013

Released

25. 8. 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

109

Pages to

113

Pages count

5

URL

BibTex

@inproceedings{BUT103552,
  author="Shakti Prasad {Rath} and Daniel {Povey} and Karel {Veselý} and Jan {Černocký}",
  title="Improved Feature Processing for 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="109--113",
  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/rath2_interspeech2013_IS130300.pdf"
}