Detail publikace

Bayesian phonotactic language model for acoustic unit discovery

ONDEL YANG, L. BURGET, L. ČERNOCKÝ, J. KESIRAJU, S.

Originální název

Bayesian phonotactic language model for acoustic unit discovery

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

Recent work on Acoustic Unit Discovery (AUD) has led to the development of a non-parametric Bayesian phone-loop model where the prior over the probability of the phone-like units is assumed to be sampled from a Dirichlet Process (DP). In this work, we propose to improve this model by incorporating a Hierarchical Pitman-Yor based bigram Language Model on top of the units transitions. This new model makes use of the phonotactic context information but assumes a fixed number of units. To remedy this limitation we first train a DP phoneloop model to infer the number of units, then, the bigram phone-loop is initialized from the DP phone-loop and trained until convergence of its parameters. Results show an absolute improvement of 1-2%on the Normalized Mutual Information (NMI) metric. Furthermore, we show that, combined with Multilingual Bottleneck (MBN) features the model yields a same or higher NMI as an English phone recogniser trained on TIMIT.

Klíčová slova

Bayesian non-parametric, Variational Bayes, acoustic unit discovery

Autoři

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

Vydáno

5. 3. 2017

Nakladatel

IEEE Signal Processing Society

Místo

New Orleans

ISBN

978-1-5090-4117-6

Kniha

Proceedings of ICASSP 2017

Strany od

5750

Strany do

5754

Strany počet

5

URL

BibTex

@inproceedings{BUT144452,
  author="Lucas Antoine Francois {Ondel} and Lukáš {Burget} and Jan {Černocký} and Santosh {Kesiraju}",
  title="Bayesian phonotactic language model for acoustic unit discovery",
  booktitle="Proceedings of ICASSP 2017",
  year="2017",
  pages="5750--5754",
  publisher="IEEE Signal Processing Society",
  address="New Orleans",
  doi="10.1109/ICASSP.2017.7953258",
  isbn="978-1-5090-4117-6",
  url="https://www.fit.vut.cz/research/publication/11472/"
}