INTERSPEECH 2004 - ICSLP
8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

Stop Consonant Classification by Dynamic Formant Trajectory

Yanli Zheng, Mark Hasegawa-Johnson, Sarah Borys

University of Illinois at Urbana-Champaign, USA

LPC analysis is one of the most powerful techniques in speech analysis. Spectral zeros during consonant or consonant-vowel transition regions introduce difficulties in estimating LPC parameters. In this paper, we propose to estimate formant frequencies from LPC model by MUSIC (Multiple Signal Classification) and ESPRIT (Estimation of Signal Parameters via Rotational Invariance Techniques). Formant candidates estimated by LS (Least Square), MUSIC and ESPRIT are combined to find an optimal solution. The effectiveness of this algorithm is verified by place classification task of stop consonants.

Full Paper

Bibliographic reference.  Zheng, Yanli / Hasegawa-Johnson, Mark / Borys, Sarah (2004): "Stop consonant classification by dynamic formant trajectory", In INTERSPEECH-2004, 2481-2484.