Detail publikačního výsledku

Factorization of Discriminatively Trained i-Vector Extractor for Speaker Recognition

NOVOTNÝ, O.; PLCHOT, O.; GLEMBEK, O.; BURGET, L.

Originální název

Factorization of Discriminatively Trained i-Vector Extractor for Speaker Recognition

Anglický název

Factorization of Discriminatively Trained i-Vector Extractor for Speaker Recognition

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

In this work, we continue in our research on i-vector extractorfor speaker verification (SV) and we optimize its architecturefor fast and effective discriminative training. We were motivatedby computational and memory requirements caused bythe large number of parameters of the original generative ivectormodel. Our aim is to preserve the power of the originalgenerative model, and at the same time focus the model towardsextraction of speaker-related information. We show that it ispossible to represent a standard generative i-vector extractor bya model with significantly less parameters and obtain similarperformance on SV tasks. We can further refine this compactmodel by discriminative training and obtain i-vectors that leadto better performance on various SV benchmarks representingdifferent acoustic domains.

Anglický abstrakt

In this work, we continue in our research on i-vector extractorfor speaker verification (SV) and we optimize its architecturefor fast and effective discriminative training. We were motivatedby computational and memory requirements caused bythe large number of parameters of the original generative ivectormodel. Our aim is to preserve the power of the originalgenerative model, and at the same time focus the model towardsextraction of speaker-related information. We show that it ispossible to represent a standard generative i-vector extractor bya model with significantly less parameters and obtain similarperformance on SV tasks. We can further refine this compactmodel by discriminative training and obtain i-vectors that leadto better performance on various SV benchmarks representingdifferent acoustic domains.

Klíčová slova

SRE

Klíčová slova v angličtině

SRE

Autoři

NOVOTNÝ, O.; PLCHOT, O.; GLEMBEK, O.; BURGET, L.

Rok RIV

2020

Vydáno

15.09.2019

Nakladatel

International Speech Communication Association

Místo

Graz

Kniha

Proceedings of Interspeech

ISSN

1990-9772

Periodikum

Proceedings of Interspeech

Svazek

2019

Číslo

9

Stát

Francouzská republika

Strany od

4330

Strany do

4334

Strany počet

5

URL

https://www.isca-speech.org/archive/Interspeech_2019/pdfs/1757.pdf

BibTex

@inproceedings{BUT159998,
  author="Ondřej {Novotný} and Oldřich {Plchot} and Ondřej {Glembek} and Lukáš {Burget}",
  title="Factorization of Discriminatively Trained i-Vector Extractor for Speaker Recognition",
  booktitle="Proceedings of Interspeech",
  year="2019",
  journal="Proceedings of Interspeech",
  volume="2019",
  number="9",
  pages="4330--4334",
  publisher="International Speech Communication Association",
  address="Graz",
  doi="10.21437/Interspeech.2019-1757",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/Interspeech_2019/pdfs/1757.pdf"
}

Dokumenty

novotny_is2019_191757