Publication Details

Unsupervised Word Segmentation from Speech with Attention

GODARD, P.; BOITO, M.; ONDEL YANG, L.; BERARD, A.; YVON, F.; VILLAVICENCIO, A.; BESACIER, L. Unsupervised Word Segmentation from Speech with Attention. In Proceeding of Interspeech 2018. Proceedings of Interspeech. Hyderabad: International Speech Communication Association, 2018. p. 2678-2682. ISSN: 1990-9772.
Czech title
Segmentace řeči na slova bez supervize s pozornostním modelem
Type
conference paper
Language
English
Authors
GODARD, P.
BOITO, M.
ONDEL YANG, L.
BERARD, A.
YVON, F.
VILLAVICENCIO, A.
BESACIER, L.
URL
Keywords

computational language documentation,encoder-decoder models, attentional models, unsupervised word segmentation.

Abstract

We present a first attempt to perform attentional word segmentation directly from the speech signal, with the final goal to automatically identify lexical units in a low-resource, unwritten language (UL). Our methodology assumes a pairing between recordings in the UL with translations in a well-resourced language. It uses Acoustic Unit Discovery (AUD) to convert speech into a sequence of pseudo-phones that is segmented using neural soft-alignments produced by a neural machine translation model. Evaluation uses an actual Bantu UL, Mboshi; comparisons to monolingual and bilingual baselines illustrate the potential of attentional word segmentation for language documentation.

Published
2018
Pages
2678–2682
Journal
Proceedings of Interspeech, vol. 2018, no. 9, ISSN 1990-9772
Proceedings
Proceeding of Interspeech 2018
Publisher
International Speech Communication Association
Place
Hyderabad
DOI
UT WoS
000465363900561
EID Scopus
BibTeX
@inproceedings{BUT163406,
  author="GODARD, P. and BOITO, M. and ONDEL YANG, L. and BERARD, A. and YVON, F. and VILLAVICENCIO, A. and BESACIER, L.",
  title="Unsupervised Word Segmentation from Speech with Attention",
  booktitle="Proceeding of Interspeech 2018",
  year="2018",
  journal="Proceedings of Interspeech",
  volume="2018",
  number="9",
  pages="2678--2682",
  publisher="International Speech Communication Association",
  address="Hyderabad",
  doi="10.21437/Interspeech.2018-1308",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/Interspeech_2018/pdfs/1308.pdf"
}
Back to top