Please use this identifier to cite or link to this item:
|Title:||Discriminative product-of-expert acoustic mapping for cross-lingual phone recognition|
|Citation:||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|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Aug 10, 2018
WEB OF SCIENCETM
checked on Jul 9, 2018
checked on Jul 27, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.