Publication Details

A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery

YUSUF, B.; ONDEL YANG, L.; BURGET, L.; ČERNOCKÝ, J.; SARAÇLAR, M. A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery. In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Toronto, Ontario: IEEE Signal Processing Society, 2021. p. 3710-3714. ISBN: 978-1-7281-7605-5.
Czech title
Jazykově adaptovaný hierarchický podprostorový model pro objevování akustických jednotek
Type
conference paper
Language
English
Authors
Yusuf Bolaji (DCGM)
ONDEL YANG, L.
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
SARAÇLAR, M.
URL
Keywords

acoustic unit discovery, hierarchical subspace model, unsupervised learning

Abstract

In this work, we propose a hierarchical subspace model for acoustic unit discovery. In this approach, we frame the task as one of learning embeddings on a low-dimensional phonetic subspace, and simultaneously specify the subspace itself as an embedding on a hyper- subspace. We train the hyper-subspace on a set of transcribed languages and transfer it to the target language. In the target language, we infer both the language and unit embeddings in an unsupervised manner, and in so doing, we simultaneously learn a subspace of units specific to that language and the units that dwell on it. We conduct experiments on TIMIT and two low-resource languages: Mboshi and Yoruba. Results show that our model outperforms major acoustic unit discovery techniques, both in terms of clustering quality and segmentation accuracy.

Published
2021
Pages
3710–3714
Proceedings
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ISBN
978-1-7281-7605-5
Publisher
IEEE Signal Processing Society
Place
Toronto, Ontario
DOI
UT WoS
000704288403193
EID Scopus
BibTeX
@inproceedings{BUT175792,
  author="YUSUF, B. and ONDEL YANG, L. and BURGET, L. and ČERNOCKÝ, J. and SARAÇLAR, M.",
  title="A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery",
  booktitle="ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",
  year="2021",
  pages="3710--3714",
  publisher="IEEE Signal Processing Society",
  address="Toronto, Ontario",
  doi="10.1109/ICASSP39728.2021.9414899",
  isbn="978-1-7281-7605-5",
  url="https://www.fit.vut.cz/research/publication/12523/"
}
Back to top