Publication result detail

Variational Inference for Acoustic Unit Discovery

ONDEL YANG, L.; BURGET, L.; ČERNOCKÝ, J.

Original Title

Variational Inference for Acoustic Unit Discovery

English Title

Variational Inference for Acoustic Unit Discovery

Type

Paper in proceedings (conference paper)

Original Abstract

In this article we proposed to train a nonparametric Bayesian model for automatic units discovery within the Variational Bayesframework. Besides simplifying the training scheme, this approach proves to be fast and yields better solution whichmakes it more suitable for big databases. However, despite the improvement observed, the model still have difficultieswith the diversity of speech and tends to learn a large part of unwanted variability. The HMM model for speechsegment is convenient but unrealistic and most likely, stronger model will be needed if one wants to achieve accurate automatic units discovery. We plan to extent the present work by using the VB inference with more complex models, as in13, and to gain leverage of Bayesian language models14 to further improve the accuracy of the discovered units.

English abstract

In this article we proposed to train a nonparametric Bayesian model for automatic units discovery within the Variational Bayesframework. Besides simplifying the training scheme, this approach proves to be fast and yields better solution whichmakes it more suitable for big databases. However, despite the improvement observed, the model still have difficultieswith the diversity of speech and tends to learn a large part of unwanted variability. The HMM model for speechsegment is convenient but unrealistic and most likely, stronger model will be needed if one wants to achieve accurate automatic units discovery. We plan to extent the present work by using the VB inference with more complex models, as in13, and to gain leverage of Bayesian language models14 to further improve the accuracy of the discovered units.

Keywords

Bayesian non-parametric, Variational Bayes, acoustic unit discovery

Key words in English

Bayesian non-parametric, Variational Bayes, acoustic unit discovery

Authors

ONDEL YANG, L.; BURGET, L.; ČERNOCKÝ, J.

RIV year

2018

Released

09.07.2016

Publisher

Elsevier Science

Location

Yogyakarta

Book

Procedia Computer Science

ISBN

1877-0509

Periodical

Procedia Computer Science

Volume

2016

Number

81

State

Kingdom of the Netherlands

Pages from

80

Pages to

86

Pages count

7

URL

http://www.sciencedirect.com/science/article/pii/S1877050916300473

BibTex

@inproceedings{BUT131006,
  author="Lucas Antoine Francois {Ondel} and Lukáš {Burget} and Jan {Černocký}",
  title="Variational Inference for Acoustic Unit Discovery",
  booktitle="Procedia Computer Science",
  year="2016",
  journal="Procedia Computer Science",
  volume="2016",
  number="81",
  pages="80--86",
  publisher="Elsevier Science",
  address="Yogyakarta",
  doi="10.1016/j.procs.2016.04.033",
  issn="1877-0509",
  url="http://www.sciencedirect.com/science/article/pii/S1877050916300473"
}

Documents

ondel_sltu2016_17-8037