Článek ve sborníku konference

HANNEMANN Mirko, TRMAL Jan, ONDEL Lucas, KESIRAJU Santosh a BURGET Lukáš. Bayesian joint-sequence models for grapheme-to-phoneme conversion. In: Proceedings of ICASSP 2017. New Orleans: IEEE Signal Processing Society, 2017, s. 2836-2840. ISBN 978-1-5090-4117-6.
Jazyk publikace:angličtina
Název publikace:Bayesian joint-sequence models for grapheme-to-phoneme conversion
Název (cs):Bayesovské modelování sdružených sekvencí pro převod grafémů na fonémy
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/hannemann_icassp2017_0002836.pdf [PDF]
Klíčová slova
Bayesian approach, joint-sequence models, weighted finite state transducers, letter-to-sound, grapheme-tophoneme conversion, hierarchical Pitman-Yor-Process
Článek pojednává o Bayesovském modelování sdružených sekvencí pro převod grafémů na fonémy, založeném na joint-sequence modelu (JSM).
We describe a fully Bayesian approach to grapheme-to-phoneme conversion based on the joint-sequence model (JSM). Usually, standard smoothed n-gram language models (LM, e.g. Kneser-Ney) are used with JSMs to model graphone sequences (joint graphemephoneme pairs). However, we take a Bayesian approach using a hierarchical Pitman-Yor-Process LM. This provides an elegant alternative to using smoothing techniques to avoid over-training. No held-out sets and complex parameter tuning is necessary, and several convergence problems encountered in the discounted Expectation- Maximization (as used in the smoothed JSMs) are avoided. Every step is modeled by weighted finite state transducers and implemented with standard operations from the OpenFST toolkit. We evaluate our model on a standard data set (CMUdict), where it gives comparable results to the previously reported smoothed JSMs in terms of phoneme-error rate while requiring a much smaller training/ testing time. Most importantly, our model can be used in a Bayesian framework and for (partly) un-supervised training.
   author = {Mirko Hannemann and Jan Trmal and Lucas Ondel and
	Santosh Kesiraju and Luk{\'{a}}{\v{s}} Burget},
   title = {Bayesian joint-sequence models for
	grapheme-to-phoneme conversion},
   pages = {2836--2840},
   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.2017.7952674},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.cs?id=11469}

Vaše IPv4 adresa: