Chinese dialect identification using segmental and prosodic features

Several approaches to Chinese dialect identification based on segmental and prosodic features of speech are described in this paper. When using segmen tal information only, the system performs phonotactic analysis after speech utterances have been tokenized into sequences of broad phonetic classes. T he second scheme comprises prosodic models which are trained to capture ton e sequence information for individual dialects. Also proposed is a novel ap proach that examines differences between Chinese dialects at broad phonetic and prosodic levels. These algorithms were evaluated via a multispeaker re ad-speech mode. Simulation results indicate that the combined use of Segmen tal and prosodic features allows the proposed system to discriminate among three major Chinese dialects spoken in Taiwan with 93.0% accuracy. (C) 2000 Acoustical Society of America. [S0001-4966(oo)03410-X].