Faculty of Information Technology, BUT

Publication Details

Bayesian Models for Unit Discovery on a Very Low Resource Language

ONDEL Lucas, GODARD Pierre, BESACIER Laurent, LARSEN Elin, HASEGAWA-JOHNSON Mark, SCHARENBORG Odette, DUPOUX Emmanuel, BURGET Lukáš, YVON Francois and KHUDANPUR Sanjeev. Bayesian Models for Unit Discovery on a Very Low Resource Language. In: Proceedings of ICASSP 2018. Calgary: IEEE Signal Processing Society, 2018, pp. 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 Lucas, Mgr. (DCGM FIT BUT)
Godard Pierre (LIMSI)
Besacier Laurent (UGA)
Larsen Elin (INRIA)
Hasegawa-Johnson Mark (UILLINOIS)
Scharenborg Odette (RUN)
Dupoux Emmanuel (ENS)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Yvon Francois (GET/ENST)
Khudanpur Sanjeev (JHU)
URL
Keywords
Acoustic Unit Discovery, Low-Resource ASR, Bayesian Model, Informative Prior.
Abstract
Developing speech technologies for low-resource languages has become a very active research field over the last decade. Among others, Bayesian models have shown some promising results on artificial examples but still lack of in situ experiments. Our work applies state-of-the-art Bayesian models to unsupervised Acoustic Unit Discovery (AUD) in a real low-resource language scenario. We also show that Bayesian models can naturally integrate information from other resourceful languages by means of informative prior leading to more consistent discovered units. Finally, discovered acoustic units are used, either as the 1-best sequence or as a lattice, to perform word segmentation. Word segmentation results show that this Bayesian approach clearly outperforms a 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, CA
DOI
BibTeX
@INPROCEEDINGS{FITPUB11719,
   author = "Lucas Ondel and Pierre Godard and Laurent Besacier and Elin Larsen and Mark Hasegawa-Johnson and Odette Scharenborg and Emmanuel Dupoux and Luk\'{a}\v{s} Burget and Francois Yvon and Sanjeev Khudanpur",
   title = "Bayesian Models for Unit Discovery on a Very Low Resource Language",
   pages = "5939--5943",
   booktitle = "Proceedings of ICASSP 2018",
   year = 2018,
   location = "Calgary, CA",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-1-5386-4658-8",
   doi = "10.1109/ICASSP.2018.8461545",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11719"
}
Back to top