Detail publikace

Improved Feature Processing for Deep Neural Networks

Originální název

Improved Feature Processing for Deep Neural Networks

Anglický název

Improved Feature Processing for Deep Neural Networks

Jazyk

en

Originální abstrakt

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

Anglický abstrakt

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

BibTex


@inproceedings{BUT103552,
  author="Shakti Prasad {Rath} and Daniel {Povey} and Karel {Veselý} and Jan {Černocký}",
  title="Improved Feature Processing for Deep Neural Networks",
  annote="In this paper, we explore various methods of providing higherdimensional features
to DNNs, while still applying speaker adaptation with fMLLR of low
dimensionality.",
  address="International Speech Communication Association",
  booktitle="Proceedings of Interspeech 2013",
  chapter="103552",
  edition="NEUVEDEN",
  howpublished="print",
  institution="International Speech Communication Association",
  number="8",
  year="2013",
  month="august",
  pages="109--113",
  publisher="International Speech Communication Association",
  type="conference paper"
}