Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Automatic Initial/Final Generation for Dialectal Chinese Speech Recognition

Linquan Liu, Thomas Fang Zheng, Wenhu Wu

Tsinghua University, China

Phonetic differences always exist between any Chinese dialect and standard Chinese (Putonghua). In this paper, a method, named automatic dialect-specific Initial/Final (IF) generation, is proposed to deal with the issue of phonemic difference which can automatically produce the dialect-specific units based on model distance measure. A dialect-specific decision tree regrowing method is also proposed to cope with the tri-IF expansion due to the introduction of dialect-specific IFs (DIFs). In combination with a certain adaptation technique, the proposed methods can achieve a syllable error rate (SER) reduction of 18.5% for Shanghai-accented Chinese compared with the Putonghua-based baseline while the use of the DIF set only can lead to an SER reduction of 5.5%.

Full Paper

Bibliographic reference.  Liu, Linquan / Zheng, Thomas Fang / Wu, Wenhu (2006): "Automatic initial/final generation for dialectal Chinese speech recognition", In INTERSPEECH-2006, paper 1051-Mon1BuP.10.