ISCA Archive Interspeech 2007
ISCA Archive Interspeech 2007

An automatic prosody labeling method for Mandarin speech

Chen-Yu Chiang, Hsiu-Min Yu, Yih-Ru Wang, Sin-Horng Chen

A new model-based automatic prosody labeling method for Mandarin speech is proposed. It first introduces four models to describe the relationships of the prosody tags to be labeled, the prosodic features of the speech signals, and the linguistic features of the associated texts. It then employs a sequential optimization procedure to estimate parameters of these four models and find all prosody tags. Experimental results on the Sinica Tree-Bank corpus showed that most prosody tags labeled were meaningful and the estimated parameters of these four models matched well with our a priori knowledge about Mandarin prosody.


doi: 10.21437/Interspeech.2007-227

Cite as: Chiang, C.-Y., Yu, H.-M., Wang, Y.-R., Chen, S.-H. (2007) An automatic prosody labeling method for Mandarin speech. Proc. Interspeech 2007, 494-497, doi: 10.21437/Interspeech.2007-227

@inproceedings{chiang07_interspeech,
  author={Chen-Yu Chiang and Hsiu-Min Yu and Yih-Ru Wang and Sin-Horng Chen},
  title={{An automatic prosody labeling method for Mandarin speech}},
  year=2007,
  booktitle={Proc. Interspeech 2007},
  pages={494--497},
  doi={10.21437/Interspeech.2007-227}
}