Please use this identifier to cite or link to this item: https://doi.org/10.1109/ASRU.2009.5372910
Title: Discriminative product-of-expert acoustic mapping for cross-lingual phone recognition
Authors: Sim, K.C. 
Issue Date: 2009
Source: Sim, K.C. (2009). Discriminative product-of-expert acoustic mapping for cross-lingual phone recognition. Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2009 : 546-551. ScholarBank@NUS Repository. https://doi.org/10.1109/ASRU.2009.5372910
Abstract: This paper presents a Product-of-Expert framework to perform probabilistic acoustic mapping for cross-lingual phone recognition. Under this framework, the posterior probabilities of the target HMM states are modelled as the weighted product of experts, where the experts or their weights are modelled as functions of the posterior probabilities of the source HMM states generated by a foreign phone recogniser. Careful choice of these functions leads to the Product-of-Posterior and Posterior Weighted Product-of-Expert models, which can be conveniently represented as 2-layer and 3-layer feed-forward neural networks respectively. Therefore, the commonly used error back-propagation method can be used to discriminatively train the model parameters. Experimental results are presented on the NTIMIT database using the Czech, Hungarian and Russian hybrid NN/HMM recognisers as the foreign phone recognisers to recognise English phones. With only about 15.6 minutes of training data, the best acoustic mapping model achieved 46.00% phone error rate, which is not far behind the 43.55% performance of the NN/HMM system trained directly on the full 3.31 hours of data. © 2009 IEEE.
Source Title: Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2009
URI: http://scholarbank.nus.edu.sg/handle/10635/41057
ISBN: 9781424454792
DOI: 10.1109/ASRU.2009.5372910
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

22
checked on Dec 6, 2017

WEB OF SCIENCETM
Citations

16
checked on Nov 19, 2017

Page view(s)

51
checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.