Title :
Using KL-divergence and multilingual information to improve ASR for under-resourced languages
Author :
Imseng, David ; Bourlard, Hervé ; Garner, Philip N.
Author_Institution :
Idiap Res. Inst., Martigny, Switzerland
Abstract :
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.
Keywords :
Gaussian processes; hidden Markov models; speech recognition; ASR improvement; Gaussian mixture model; Greek SpeechDat data; HMM-GMM system; KL-divergence; Kullback-Leibler divergence based method; automatic speech recognition; hidden Markov model; hybrid Tandem-like system; multilingual information; under-resourced languages; universal phoneme posterior probabilities; Accuracy; Acoustics; Hidden Markov models; Speech; Speech recognition; Training; Training data; Kullback-Leibler divergence; Multilingual speech recognition; fast training; neural network features;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4673-0045-2
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2012.6289010