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. 57505754. ISBN 9781509041176. 
Publication language:  english 

Original title:  Bayesian phonotactic language model for Acoustic Unit Discovery 

Title (cs):  Bayesovský fonotaktický jazykový model pro automatické hledání řečových jednotek 

Pages:  57505754 

Proceedings:  Proceedings of ICASSP 2017 

Conference:  42nd IEEE International Conference on Acoustics, Speech and Signal Processing 

Place:  New Orleans, US 

Year:  2017 

ISBN:  9781509041176 

DOI:  10.1109/ICASSP.2017.7953258 

Publisher:  IEEE Signal Processing Society 

URL:  http://www.fit.vutbr.cz/research/groups/speech/publi/2017/ondel_icassp2017_0005750.pdf [PDF] 

Keywords 

Bayesian nonparametric, Variational Bayes, acoustic unit discovery 
Annotation 

This article is about Bayesian phonotactic language model for acoustic unit discovery (AUD), which has led to the development of a nonparametric Bayesian phoneloop model.

Abstract 

Recent work on Acoustic Unit Discovery (AUD) has led to the
development of a nonparametric Bayesian phoneloop model
where the prior over the probability of the phonelike units is
assumed to be sampled from a Dirichlet Process (DP). In this
work, we propose to improve this model by incorporating a
Hierarchical PitmanYor 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
phoneloop is initialized from the DP phoneloop and trained
until convergence of its parameters. Results show an absolute
improvement of 12%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. 
BibTeX: 

@INPROCEEDINGS{
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 = {57505754},
booktitle = {Proceedings of ICASSP 2017},
year = {2017},
location = {New Orleans, US},
publisher = {IEEE Signal Processing Society},
ISBN = {9781509041176},
doi = {10.1109/ICASSP.2017.7953258},
language = {english},
url = {http://www.fit.vutbr.cz/research/view_pub.php.en?id=11472}
} 