Publication detail

Using Gradient Descent Optimization for Acoustics Training from Heterogeneous Data

KARAFIÁT, M. SZŐKE, I. ČERNOCKÝ, J.

Original Title

Using Gradient Descent Optimization for Acoustics Training from Heterogeneous Data

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

This paper is on using the gradient descent optimization for acoustics training from heterogeneous data. We study the use of heterogeneous data for training of acoustic models.

Keywords

speech, acoustic models, heterogeneous data, HLDA system, gradient descent training, robustness

Authors

KARAFIÁT, M.; SZŐKE, I.; ČERNOCKÝ, J.

RIV year

2010

Released

6. 9. 2010

Publisher

Springer Verlag

Location

Brno

ISBN

978-3-642-15759-2

Book

Proc. Text, Speech and Dialog 2010

Edition

LNAI 6231

ISBN

0302-9743

Periodical

Lecture Notes in Computer Science

Year of study

2010

Number

9

State

Federal Republic of Germany

Pages from

322

Pages to

329

Pages count

8

URL

BibTex

@inproceedings{BUT34926,
  author="Martin {Karafiát} and Igor {Szőke} and Jan {Černocký}",
  title="Using Gradient Descent Optimization for Acoustics Training from Heterogeneous Data",
  booktitle="Proc. Text, Speech and Dialog 2010",
  year="2010",
  series="LNAI 6231",
  journal="Lecture Notes in Computer Science",
  volume="2010",
  number="9",
  pages="322--329",
  publisher="Springer Verlag",
  address="Brno",
  isbn="978-3-642-15759-2",
  issn="0302-9743",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2010/karafiat_TSD_2010_322.pdf"
}