Adaptation of acoustic models for multilingual recognition

This paper evaluates the recognition performance of a system using acoustic models transformed across language boundaries. Parameters of hidden Markov models (HMMs) trained on speaker independent English data are adapted using Afrikaans adaptation data to realise speaker dependent, multispeaker and speaker independent Afrikaans models. Adaptation is performed using maximum a posteriori probability (MAP) and maximum likelihood linear regression (MLLR) methods on context independent and context dependent phones. Results show that MLLR transformation of English models using Afrikaans adaptation data signi cantly improves model performance and for context dependent models achieves better performance on speaker independent tests than achievable by direct training on the adaptation data.