This paper addresses the problem of speech recognition under accent variations in English language. It has been demonstrated in previous research efforts that the multi-transitional model architecture is one of the solutions for robust speech recognition. In this study, we describe an universal hybrid system that is trained with data from American, Australian, and British accented speech. Experimental results on connected-digit recognition task show an average string error rate reduc-tion of about 62% and 8% when compared to our best monolingual and multi-transitional systems respectively. The result indicates that the universal model is about three times faster and half time smaller than the multi-transitional or multilingual models and this makes it an ideal choice for practical accent-independent speech recognition applications.
展开▼
