Chinese Dialect Identification Using Tone Features Based on Pitch Flux

This paper presents a method to extract tone relevant features based on pitch flux from continuous speech signal. The autocorrelations of two adjacent frames are calculated and the covariance between them is estimated to extract multi-dimensional pitch flux features. These features, together with MFCCs, are modeled in a 2-stream GMM models, and are tested in a 3-dialect identification task for Chinese. The pitch flux features have shown to be very effective in identifying tonal languages with short speech segments. For the test speech segments of 3 seconds, 2-stream model achieves more than 30% error reduction over MFCC-based model

[1]  Bin Ma,et al.  Using local & global phonotactic features in Chinese dialect identification , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[2]  Timothy J. Hazen,et al.  Segment-based automatic language identification , 1997 .

[3]  Douglas E. Sturim,et al.  The 2004 MIT Lincoln Laboratory speaker recognition system , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[4]  Hsiao-Chuan Wang,et al.  Language identification using pitch contour information , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[5]  Panayiotis G. Georgiou,et al.  Speaker identification using supra-segmental pitch pattern dynamics , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  W W Chang,et al.  Chinese dialect identification using segmental and prosodic features. , 2000, The Journal of the Acoustical Society of America.

[7]  Tan Lee,et al.  Using tone information in Cantonese continuous speech recognition , 2002, TALIP.

[8]  Frank Seide,et al.  Pitch tracking and tone features for Mandarin speech recognition , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).