Comparing different acoustic modeling techniques for multilingual boosting

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.


Year:
2013
Publisher:
Idiap
Laboratories:




 Record created 2013-12-19, last modified 2018-03-17

n/a:
Download fulltextPDF
External link:
Download fulltextRelated documents
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)