Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Accent-Specific Mandarin Adaptation Based on Pronunciation Modeling Technology

Mingkuan Liu, Bo Xu

National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China

An accent adaptation approach using pronunciation variation modeling technology for Mandarin accent was proposed in this paper. As Chinese language is monosyllabic, the syllable pronunciation variation dictionary (SPVD) was built to depict the characteristics of accent. Firstly, the pronunciation modeling technology was utilized to get the context-independent and contextdependent accent-specific syllable confusion matrix according to the acoustic recognition results (pin-yin stream). Then the accentspecific Chinese SPVD was constructed from this confusion matrix. Finally, N-Best acoustic recognition candidates were rescored with the help of SPVD. To curtail the necessary adaptation data size for context-dependent SPVD, we divided the syllable context into several groups. The experiment results show that pronunciation variation modeling technology is an effective method for Mandarin accent adaptation, and the context grouping strategy can reduce the adapting speech data effectively while keep the same satisfactory performance.


Full Paper

Bibliographic reference.  Liu, Mingkuan / Xu, Bo (2000): "Accent-specific Mandarin adaptation based on pronunciation modeling technology", In ICSLP-2000, vol.2, 330-333.