Článek ve sborníku konference

ONDEL Lucas, BURGET Lukáš, ČERNOCKÝ Jan a KESIRAJU Santosh. Bayesian phonotactic language model for Acoustic Unit Discovery. In: Proceedings of ICASSP 2017. New Orleans: IEEE Signal Processing Society, 2017, s. 5750-5754. ISBN 978-1-5090-4117-6.
Jazyk publikace:angličtina
Název publikace:Bayesian phonotactic language model for Acoustic Unit Discovery
Název (cs):Bayesovský fonotaktický jazykový model pro automatické hledání řečových jednotek
Sborník:Proceedings of ICASSP 2017
Konference:42nd IEEE International Conference on Acoustics, Speech and Signal Processing
Místo vydání:New Orleans, US
Vydavatel:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2017/ondel_icassp2017_0005750.pdf [PDF]
Klíčová slova
Bayesian non-parametric, Variational Bayes, acoustic unit discovery
Článek pojednává o Bayesovském fonotaktickém jazykovém modelu pro automatické hledání řečových jednotek.
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.
   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 = {http://www.fit.vutbr.cz/research/view_pub.php.cs?id=11472}

Vaše IPv4 adresa: