Publication detail

BUT/Phonexia Bottleneck Feature Extractor

SILNOVA, A. MATĚJKA, P. GLEMBEK, O. PLCHOT, O. NOVOTNÝ, O. GRÉZL, F. SCHWARZ, P. ČERNOCKÝ, J.

Original Title

BUT/Phonexia Bottleneck Feature Extractor

English Title

BUT/Phonexia Bottleneck Feature Extractor

Type

conference paper

Language

en

Original Abstract

This paper complements the public release of the BUT/Phonexia bottleneck (BN) feature extractor. Starting with a brief history of Neural Network (NN)-based and BN-based approaches to speech feature extraction, it describes the structure of the released software. It follows by describing the three provided NNs: the first two trained on the US English Fisher corpus with monophone-state and tied-state targets, and the third network trained in a multi-lingual fashion on 17 Babel languages. The NNs were technically trained to classify acoustic units, however the networks were optimized with respect to the language recognition task, which is the main focus of this paper. Nevertheless, it is worth noting that apart from language recognition, the provided software can be used with any speech-related task. The paper concludes with a comprehensive summary of the results obtained on the NIST 2015 and 2017 Language Recognition Evaluations tasks.

English abstract

This paper complements the public release of the BUT/Phonexia bottleneck (BN) feature extractor. Starting with a brief history of Neural Network (NN)-based and BN-based approaches to speech feature extraction, it describes the structure of the released software. It follows by describing the three provided NNs: the first two trained on the US English Fisher corpus with monophone-state and tied-state targets, and the third network trained in a multi-lingual fashion on 17 Babel languages. The NNs were technically trained to classify acoustic units, however the networks were optimized with respect to the language recognition task, which is the main focus of this paper. Nevertheless, it is worth noting that apart from language recognition, the provided software can be used with any speech-related task. The paper concludes with a comprehensive summary of the results obtained on the NIST 2015 and 2017 Language Recognition Evaluations tasks.

Keywords

bottlneck feature extractor, speech recognition, language recognition

Released

26.06.2018

Publisher

International Speech Communication Association

Location

Les Sables d´Olonne

ISBN

2312-2846

Periodical

Proceedings of Odyssey: The Speaker and Language Recognition Workshop Odyssey 2014, Joensuu, Finland

Year of study

2018

Number

6

State

FI

Pages from

283

Pages to

287

Pages count

5

URL

Documents

BibTex


@inproceedings{BUT155076,
  author="Anna {Silnova} and Pavel {Matějka} and Ondřej {Glembek} and Oldřich {Plchot} and Ondřej {Novotný} and František {Grézl} and Petr {Schwarz} and Jan {Černocký}",
  title="BUT/Phonexia Bottleneck Feature Extractor",
  annote="This paper complements the public release of the BUT/Phonexia bottleneck (BN)
feature extractor. Starting with a brief history of Neural Network (NN)-based and
BN-based approaches to speech feature extraction, it describes the structure of
the released software. It follows by describing the three provided NNs: the first
two trained on the US English Fisher corpus with monophone-state and tied-state
targets, and the third network trained in a multi-lingual fashion on 17 Babel
languages. The NNs were technically trained to classify acoustic units, however
the networks were optimized with respect to the language recognition task, which
is the main focus of this paper. Nevertheless, it is worth noting that apart from
language recognition, the provided software can be used with any speech-related
task. The paper concludes with a comprehensive summary of the results obtained on
the NIST 2015 and 2017 Language Recognition Evaluations tasks.",
  address="International Speech Communication Association",
  booktitle="Proceedings of Odyssey 2018",
  chapter="155076",
  doi="10.21437/Odyssey.2018-40",
  edition="NEUVEDEN",
  howpublished="online",
  institution="International Speech Communication Association",
  number="6",
  year="2018",
  month="june",
  pages="283--287",
  publisher="International Speech Communication Association",
  type="conference paper"
}