Using KL-divergence and multilingual information to improve ASR for under-resourced languages

Setting out from the point of view that automatic speech recognition (ASR) ought to benefit from data in languages other than the target language, we propose a novel Kullback-Leibler (KL) divergence based method that is able to exploit multilingual information in the form of universal phoneme poster...

Full description

Saved in:
Bibliographic Details
Main Authors: Imseng, D., Bourlard, H., Garner, P. N.
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Acoustics
fast training
Hidden Markov models
Kullback-Leibler divergence
Multilingual speech recognition
neural network features
Speech
Speech recognition
Training
Training data
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Setting out from the point of view that automatic speech recognition (ASR) ought to benefit from data in languages other than the target language, we propose a novel Kullback-Leibler (KL) divergence based method that is able to exploit multilingual information in the form of universal phoneme posterior probabilities conditioned on the acoustics. We formulate a means to train a recognizer on several different languages, and subsequently recognize speech in a target language for which only a small amount of data is available. Taking the Greek SpeechDat(II) data as an example, we show that the proposed formulation is sound, and show that it is able to out-perform a current state-of-the-art HMM/GMM system. We also use a hybrid Tandem-like system to further understand the source of the benefit.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2012.6289010