Publication Details

Bayesian phonotactic language model for Acoustic Unit Discovery

ONDEL Lucas, BURGET Lukáš, ČERNOCKÝ Jan and KESIRAJU Santosh. Bayesian phonotactic language model for acoustic unit discovery. In: Proceedings of ICASSP 2017. New Orleans: IEEE Signal Processing Society, 2017, pp. 5750-5754. ISBN 978-1-5090-4117-6.
Czech title
Bayesovský fonotaktický jazykový model pro automatické hledání řečových jednotek
Type
conference paper
Language
english
Authors
Ondel Lucas, Mgr. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, doc. Dr. Ing. (DCGM FIT BUT)
Kesiraju Santosh (IIIT)
URL
Keywords
Bayesian non-parametric, Variational Bayes, acoustic unit discovery
Abstract
This article is about Bayesian phonotactic language model for acoustic unit discovery (AUD), which has led to the development of a non-parametric Bayesian phone-loop model.
Annotation
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.
Published
2017
Pages
5750-5754
Proceedings
Proceedings of ICASSP 2017
Conference
42nd IEEE International Conference on Acoustics, Speech and Signal Processing, New Orleans, USA, US
ISBN
978-1-5090-4117-6
Publisher
IEEE Signal Processing Society
Place
New Orleans, US
DOI
BibTeX
@INPROCEEDINGS{FITPUB11472,
   author = "Lucas Ondel and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y} and Santosh Kesiraju",
   title = "Bayesian phonotactic language model for Acoustic Unit Discovery",
   pages = "5750--5754",
   booktitle = "Proceedings of ICASSP 2017",
   year = 2017,
   location = "New Orleans, US",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-1-5090-4117-6",
   doi = "10.1109/ICASSP.2017.7953258",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11472"
}
Back to top