Stop classification using DESA-1 high resolution formant tracking

The results using the DESA-1 (discrete energy separation algorithm-1) quadratic frequency estimator to determine the frequency and rate of change of the second-formant frequency are shown. It is shown for different vowel environments that the DESA-1 algorithm can extract sufficient information to classify stops from vocalic data. The performance is demonstrated to be superior to that of a formant tracker using a more conventional pitch-synchronous LPC (linear predictive coding) analysis. The DESA-1 method is computationally simple enough to be performed in real time.<<ETX>>

[1]  A. Liberman,et al.  Acoustic Loci and Transitional Cues for Consonants , 1954 .

[2]  Petros Maragos,et al.  Speech nonlinearities, modulations, and energy operators , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[3]  Harvey F. Silverman,et al.  A time-varying analysis method for rapid transitions in speech , 1991, IEEE Trans. Signal Process..

[4]  Pietro Laface,et al.  Computer recognition of plosive sounds using contextual information , 1983 .

[5]  P. Mermelstein,et al.  Speech sounds and features , 1975, Proceedings of the IEEE.

[6]  Victor Zue,et al.  Selecting acoustic features for stop consonant identification , 1983, ICASSP.

[7]  Philip Lieberman,et al.  Speech Physiology, Speech Perception, and Acoustic Phonetics , 1988 .

[8]  Petros Maragos,et al.  On separating amplitude from frequency modulations using energy operators , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[9]  D. Kewley-Port.  Measurement of formant transitions in naturally produced stop consonant-vowel syllables. , 1982, The Journal of the Acoustical Society of America.