INTERSPEECH 2006 - ICSLP
Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Formant-Based English Vowel Assessment for Chinese in Taiwan

Jiang-Chun Chen (1), Wei-Tang Hsu (1), J.-S. Roger Jang (1), Ren-Yuan Lyu (2), Yuang-Chin Chiang (1)

(1) National Tsing Hua University, Taiwan; (2) Chang Gung University, Taiwan

This paper proposes a formant-based approach for computer-assisted English vowel assessment. Various studies in formant-based speech synthesis have suggested the importance of formant coefficients; this motivates us to investigate pronunciation assessment using formant information instead of MFCC (Mel-frequency cepstral coefficients) alone. In particular, we explore the multi-stream HMM with the addition of formant information to improve the phoneme segmentation. We then propose the use of PCN (pronunciation confusion network) together with a formant-based confidence measure to improve error detection rates. Furthermore, the pros and cons of using cross-word phone model for both native speakers and L2 learners are discussed. Experimental results demonstrate the feasibility of the proposed approach for automatic vowel pronunciation assessment.

Full Paper

Bibliographic reference.  Chen, Jiang-Chun / Hsu, Wei-Tang / Jang, J.-S. Roger / Lyu, Ren-Yuan / Chiang, Yuang-Chin (2006): "Formant-based English vowel assessment for Chinese in Taiwan", In INTERSPEECH-2006, paper 1968-Tue3CaP.6.