In this paper, a novel approach is proposed to analyze prosodic features of four Chinese dialects: Wu, Cantonese, Min and Mandarin. The ultimate goal is to exploit these features in the task of automatic spoken language identification. Two entropy-based evaluation metrics are formulated to address the problems of data sparseness and lack of speakers. Different prosody-related acoustic features and their combinations are evaluated. F0, F0 gradient and intensity are found to contain the most language-related information. Maximum language-related information are observed in multi-dimensional N-gram features with F0, F0 gradient and syllable position in sentence. There are also some uncertain results that reveal the limitations of the proposed metrics. Index Terms— Chinese dialect identification, prosody, Cantonese, Mandarin, Min, Wu
Cite as: Ng, R.W.M., Lee, T. (2008) Entropy-based Analysis of The Prosodic Features of Chinese Dialects. Proc. International Symposium on Chinese Spoken Language Processing, 65-68
@inproceedings{ng08_iscslp,
author={Raymond W. M. Ng and Tan Lee},
title={{Entropy-based Analysis of The Prosodic Features of Chinese Dialects}},
year=2008,
booktitle={Proc. International Symposium on Chinese Spoken Language Processing},
pages={65--68}
}