Modified polyphone decision tree specialization for porting multilingual Grapheme based ASR systems to new languages

Automatic speech recognition (ASR) systems have been developed only for a very limited number of the estimated 7,000 languages in the world. In order to avoid the evolvement of a digital divide between languages for which ASR systems exist and those without one, it is necessary to be able to rapidly create ASR systems for new languages in a cost efficient way. Grapheme based systems, which eliminate the costly need for a pronunciation dictionary, have been shown to work for a variety of languages. They are thus destined for porting ASR systems to new languages. This paper studies the use of multilingual grapheme based models for rapidly bootstrapping acoustic models in new languages. The cross language performance of a standard, multilingual (ML) acoustic model on a new language is improved by introducing a new, modified version of polyphone decision tree specialization that improves the performance of the ML models by up to 15.5% relative.