Publication result detail

Data selection by sequence summarizing neural network in mismatch condition training

ŽMOLÍKOVÁ, K.; KARAFIÁT, M.; VESELÝ, K.; DELCROIX, M.; WATANABE, S.; BURGET, L.; ČERNOCKÝ, J.

Original Title

Data selection by sequence summarizing neural network in mismatch condition training

English Title

Data selection by sequence summarizing neural network in mismatch condition training

Type

Paper in proceedings (conference paper)

Original Abstract

Data augmentation is a simple and efficient technique to improvethe robustness of a speech recognizer when deployed inmismatched training-test conditions. Our paper proposes a newapproach for selecting data with respect to similarity of acousticconditions. The similarity is computed based on a sequencesummarizing neural network which extracts vectors containingacoustic summary (e.g. noise and reverberation characteristics)of an utterance. Several configurations of this network and differentmethods of selecting data using these "summary-vectors"were explored. The results are reported on a mismatched conditionusing AMI training set with the proposed data selectionand CHiME3 test set.

English abstract

Data augmentation is a simple and efficient technique to improvethe robustness of a speech recognizer when deployed inmismatched training-test conditions. Our paper proposes a newapproach for selecting data with respect to similarity of acousticconditions. The similarity is computed based on a sequencesummarizing neural network which extracts vectors containingacoustic summary (e.g. noise and reverberation characteristics)of an utterance. Several configurations of this network and differentmethods of selecting data using these "summary-vectors"were explored. The results are reported on a mismatched conditionusing AMI training set with the proposed data selectionand CHiME3 test set.

Keywords

Automatic speech recognition, Data augmentation,Data selection, Mismatch training condition, Sequencesummarization

Key words in English

Automatic speech recognition, Data augmentation,Data selection, Mismatch training condition, Sequencesummarization

Authors

ŽMOLÍKOVÁ, K.; KARAFIÁT, M.; VESELÝ, K.; DELCROIX, M.; WATANABE, S.; BURGET, L.; ČERNOCKÝ, J.

RIV year

2017

Released

08.09.2016

Publisher

International Speech Communication Association

Location

San Francisco

ISBN

978-1-5108-3313-5

Book

Proceedings of Interspeech 2016

Pages from

2354

Pages to

2358

Pages count

5

URL

https://www.semanticscholar.org/paper/Data-Selection-by-Sequence-Summarizing-Neural-Zmol%C3%ADkov%C3%A1-Karafi%C3%A1t/bc1832e8b8d4e5edf987e1562b578bd9aa5e18a9

BibTex

@inproceedings{BUT132600,
  author="Kateřina {Žmolíková} and Martin {Karafiát} and Karel {Veselý} and Marc {Delcroix} and Shinji {Watanabe} and Lukáš {Burget} and Jan {Černocký}",
  title="Data selection by sequence summarizing neural network in mismatch condition training",
  booktitle="Proceedings of Interspeech 2016",
  year="2016",
  pages="2354--2358",
  publisher="International Speech Communication Association",
  address="San Francisco",
  doi="10.21437/Interspeech.2016-741",
  isbn="978-1-5108-3313-5",
  url="https://www.semanticscholar.org/paper/Data-Selection-by-Sequence-Summarizing-Neural-Zmol%C3%ADkov%C3%A1-Karafi%C3%A1t/bc1832e8b8d4e5edf987e1562b578bd9aa5e18a9"
}

Documents

zmolikova_interpeech2016_IS160741