Automatic accent identification using Gaussian mixture models

It is well known that speaker variability caused by accent is an important factor io speech recognition. Some major accents in China are so different as to make this problem very severe. We propose a Gaussian mixture model (GMM) based Mandarin accent identitication method. In this method a number of GMMs are trained to identify the most likely accent given test utterances. The identified accent type can be used to select an accent-dependent model for speech recognition. A multi-accent Mandarin corpus was developed for the task, including 4 typical accents in China with 1,440 speakers (l,200 for training, 240 for testing). We explore experimentally the effect of the number of components in GMM on identification performance. We also investigate how many utterances per speaker are sufficient to reliably recognize his/her accent. Finally, we show the correlations among accents and provide some discussion.