Detail publikačního výsledku

Evaluation of SpeakerBeam target speech extraction in real noisy and reverberant conditions

DELCROIX, M.; ŽMOLÍKOVÁ, K.; OCHIAI, T.; KINOSHITA, K.; ARAKI, S.; NAKATANI, T.

Originální název

Evaluation of SpeakerBeam target speech extraction in real noisy and reverberant conditions

Anglický název

Evaluation of SpeakerBeam target speech extraction in real noisy and reverberant conditions

Druh

Článek recenzovaný mimo WoS a Scopus

Originální abstrakt

The paper discusses SpeakerBeam for target speaker extraction. The main variation is in the use of a scaling adaptation layer to adapt a neural network instead of the previously proposed factorized layer. This enables to greatly reduce the number of model parameters, without affecting performance.

Anglický abstrakt

The paper discusses SpeakerBeam for target speaker extraction. The main variation is in the use of a scaling adaptation layer to adapt a neural network instead of the previously proposed factorized layer. This enables to greatly reduce the number of model parameters, without affecting performance.

Klíčová slova

SpeakerBeam, speaker, extraction, neural network

Klíčová slova v angličtině

SpeakerBeam, speaker, extraction, neural network

Autoři

DELCROIX, M.; ŽMOLÍKOVÁ, K.; OCHIAI, T.; KINOSHITA, K.; ARAKI, S.; NAKATANI, T.

Rok RIV

2020

Vydáno

10.10.2019

ISSN

0369-4232

Periodikum

THE JOURNAL OF THE ACOUSTICAL SOCIETY OF JAPAN

Svazek

2019

Číslo

2

Stát

Japonsko

Strany od

1

Strany do

2

Strany počet

2

URL

BibTex

@article{BUT160008,
  author="DELCROIX, M. and ŽMOLÍKOVÁ, K. and OCHIAI, T. and KINOSHITA, K. and ARAKI, S. and NAKATANI, T.",
  title="Evaluation of SpeakerBeam target speech extraction in real noisy and reverberant conditions",
  journal="THE JOURNAL OF THE ACOUSTICAL SOCIETY OF JAPAN",
  year="2019",
  volume="2019",
  number="2",
  pages="1--2",
  issn="0369-4232",
  url="https://www.fit.vut.cz/research/publication/12103/"
}

Dokumenty