@inproceedings{a9401b2c5a64481c94526434f2d6c3e0,
title = "Bayesian Models for Unit Discovery on a Very Low Resource Language",
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 I-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.",
keywords = "Acoustic Unit Discovery, Bayesian Model, Informative Prior, Low-Resource ASR",
author = "Lucas Ondel and Pierre Godard and Laurent Besacier and Elin Larsen and Mark Hasegawa-Johnson and Odette Scharenborg and Emmanuel Dupoux and Lukas Burget and Francois Yvon and Sanjeev Khudanpur",
note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 ; Conference date: 15-04-2018 Through 20-04-2018",
year = "2018",
month = sep,
day = "10",
doi = "10.1109/ICASSP.2018.8461545",
language = "English (US)",
isbn = "9781538646588",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "5939--5943",
booktitle = "2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings",
address = "United States",
}