Publication Details

Bayesian Models for Unit Discovery on a Very Low Resource Language

ONDEL YANG, L.; GODARD, P.; BESACIER, L.; LARSEN, E.; HASEGAWA-JOHNSON, M.; SCHARENBORG, O.; DUPOUX, E.; BURGET, L.; YVON, F.; KHUDANPUR, S. Bayesian Models for Unit Discovery on a Very Low Resource Language. In Proceedings of ICASSP 2018. Calgary: IEEE Signal Processing Society, 2018. p. 5939-5943. ISBN: 978-1-5386-4658-8.
Czech title
Bayesovské modely pro objevování jednotek v jazycích s velmi omezenými zdroji
Type
conference paper
Language
English
Authors
ONDEL YANG, L.
GODARD, P.
BESACIER, L.
LARSEN, E.
Hasegawa-Johnson Mark
SCHARENBORG, O.
Dupoux Emmanuel
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
YVON, F.
Khudanpur Sanjeev
URL
Keywords

Acoustic Unit Discovery, Low-ResourceASR, Bayesian Model, Informative Prior.

Abstract

Developing speech technologies for low-resource languageshas become a very active research field over the last decade.Among others, Bayesian models have shown some promisingresults on artificial examples but still lack of in situ experiments.Our work applies state-of-the-art Bayesian modelsto unsupervised Acoustic Unit Discovery (AUD) in a reallow-resource language scenario. We also show that Bayesianmodels can naturally integrate information from other resourcefullanguages by means of informative prior leadingto more consistent discovered units. Finally, discoveredacoustic units are used, either as the 1-best sequence or as alattice, to perform word segmentation. Word segmentationresults show that this Bayesian approach clearly outperformsa Segmental-DTW baseline on the same corpus.

Published
2018
Pages
5939–5943
Proceedings
Proceedings of ICASSP 2018
Conference
IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, CA
ISBN
978-1-5386-4658-8
Publisher
IEEE Signal Processing Society
Place
Calgary
DOI
UT WoS
000446384606020
EID Scopus
BibTeX
@inproceedings{BUT155041,
  author="ONDEL YANG, L. and GODARD, P. and BESACIER, L. and LARSEN, E. and HASEGAWA-JOHNSON, M. and SCHARENBORG, O. and DUPOUX, E. and BURGET, L. and YVON, F. and KHUDANPUR, S.",
  title="Bayesian Models for Unit Discovery on a Very Low Resource Language",
  booktitle="Proceedings of ICASSP 2018",
  year="2018",
  pages="5939--5943",
  publisher="IEEE Signal Processing Society",
  address="Calgary",
  doi="10.1109/ICASSP.2018.8461545",
  isbn="978-1-5386-4658-8",
  url="https://www.fit.vut.cz/research/publication/11719/"
}
Files
Back to top