Publication result detail

A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery

YUSUF, B.; ONDEL YANG, L.; BURGET, L.; ČERNOCKÝ, J.; SARAÇLAR, M.

Original Title

A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery

English Title

A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery

Type

Paper in proceedings (conference paper)

Original Abstract

In this work, we propose a hierarchical subspace model for acousticunit discovery. In this approach, we frame the task as one oflearning embeddings on a low-dimensional phonetic subspace, andsimultaneously specify the subspace itself as an embedding on a hyper-subspace. We train the hyper-subspace on a set of transcribedlanguages and transfer it to the target language. In the target language,we infer both the language and unit embeddings in an unsupervisedmanner, and in so doing, we simultaneously learn a subspaceof 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 majoracoustic unit discovery techniques, both in terms of clusteringquality and segmentation accuracy.

English abstract

In this work, we propose a hierarchical subspace model for acousticunit discovery. In this approach, we frame the task as one oflearning embeddings on a low-dimensional phonetic subspace, andsimultaneously specify the subspace itself as an embedding on a hyper-subspace. We train the hyper-subspace on a set of transcribedlanguages and transfer it to the target language. In the target language,we infer both the language and unit embeddings in an unsupervisedmanner, and in so doing, we simultaneously learn a subspaceof 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 majoracoustic unit discovery techniques, both in terms of clusteringquality and segmentation accuracy.

Keywords

acoustic unit discovery, hierarchical subspacemodel, unsupervised learning

Key words in English

acoustic unit discovery, hierarchical subspacemodel, unsupervised learning

Authors

YUSUF, B.; ONDEL YANG, L.; BURGET, L.; ČERNOCKÝ, J.; SARAÇLAR, M.

RIV year

2022

Released

06.06.2021

Publisher

IEEE Signal Processing Society

Location

Toronto, Ontario

ISBN

978-1-7281-7605-5

Book

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Pages from

3710

Pages to

3714

Pages count

5

URL

https://www.fit.vut.cz/research/publication/12523/

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/"
}

Documents

yusuf_icassp2021_09414899