8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

Learning Tone Distinctions for Mandarin Chinese

David Weenink (1), Guangqin Chen (2), Zongyan Chen (3), Stefan de Konink (1), Dennis Vierkant (4), Eveline van Hagen (5), R. J. J. H. van Son (1)

(1) University of Amsterdam, The Netherlands
(2) Hogeschool Rotterdam, The Netherlands
(3) Hogeschool van Amsterdam, The Netherlands
(4) University of Twente, The Netherlands
(5) Fontys Hogescholen, The Netherlands

We describe the SpeakGoodChinese system that supports beginning students of Mandarin Chinese to produce tones correctly ( Students pronounce a word spelled in pinyin notation and receive feedback from our system on their production of the tones. The novelty in our approach lies in the use of synthetic reference tone(s) produced from the pinyin notation. Preliminary results indicate a 6% rejection rate for six words, read multiple times, by three reference speakers and less than 15% acceptance rate on incorrectly produced tones on shadowed versions of these words by 8 speakers. With speech from 4 reference speakers collected with a fully functional test application, a rejection rate of less than 15% was achieved.

Full Paper

Bibliographic reference.  Weenink, David / Chen, Guangqin / Chen, Zongyan / Konink, Stefan de / Vierkant, Dennis / Hagen, Eveline van / Son, R. J. J. H. van (2007): "Learning tone distinctions for Mandarin Chinese", In INTERSPEECH-2007, 2341-2344.