Detail publikačního výsledku

Using Gradient Descent Optimization for Acoustic Training from Heterogeneous Data

KARAFIÁT, M.; SZŐKE, I.; ČERNOCKÝ, J.

Originální název

Using Gradient Descent Optimization for Acoustic Training from Heterogeneous Data

Anglický název

Using Gradient Descent Optimization for Acoustic Training from Heterogeneous Data

Druh

Stať ve sborníku mimo WoS a Scopus

Originální abstrakt

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.

Anglický abstrakt

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.

Klíčová slova

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

Klíčová slova v angličtině

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

Autoři

KARAFIÁT, M.; SZŐKE, I.; ČERNOCKÝ, J.

Rok RIV

2011

Vydáno

06.09.2010

Nakladatel

Springer Verlag

Místo

Brno

ISBN

978-3-642-15759-2

Kniha

Proc. Text, Speech and Dialog 2010

Edice

LNAI 6231

ISSN

0302-9743

Periodikum

Lecture Notes in Computer Science

Svazek

2010

Číslo

9

Stát

Spolková republika Německo

Strany od

322

Strany do

329

Strany počet

8

URL

BibTex

@inproceedings{BUT34926,
  author="Martin {Karafiát} and Igor {Szőke} and Jan {Černocký}",
  title="Using Gradient Descent Optimization for Acoustic 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"
}