REPORT Imseng_Idiap-RR-01-2013/IDIAP Comparing different acoustic modeling techniques for multilingual boosting Imseng, David Dines, John Motlicek, Petr Garner, Philip N. Bourlard, Hervé EXTERNAL https://publications.idiap.ch/attachments/reports/2012/Imseng_Idiap-RR-01-2013.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/Imseng_INTERSPEECH_2012 Related documents Idiap-RR-01-2013 2013 Idiap January 2013 In this paper, we explore how different acoustic modeling techniques can benefit from data in languages other than the target language. We propose an algorithm to perform decision tree state clustering for the recently proposed Kullback-Leibler divergence based hidden Markov models (KL-HMM) and compare it to subspace Gaussian mixture modeling (SGMM). KL-HMM can exploit multilingual information in the form of universal phoneme posterior features and SGMM benefits from a universal background model that can be trained on multilingual data. Taking the Greek SpeechDat(II) data as an example, we show that KL-HMM performs best for small amounts of target language data. CONF Imseng_INTERSPEECH_2012/IDIAP Comparing different acoustic modeling techniques for multilingual boosting Imseng, David Dines, John Motlicek, Petr Garner, Philip N. Bourlard, Hervé multilingual acoustic modeling speech recognition under-resourced languages EXTERNAL https://publications.idiap.ch/attachments/papers/2012/Imseng_INTERSPEECH_2012.pdf PUBLIC Proceedings of Interspeech Portland, Oregon 2012