Spectral shape factors for speaker‐independent automatic recognition of stop consonants

Abstract

A series of automatic recognition experiments was conducted with naturally produced English stop consonants /b,p,d,t,g,k/ in syllable initial position. The objectives of the experiments were to investigate in detail the effectiveness of spectral shape factors, as both dynamic and static features for automatic recognition of stop consonants. Spectral shape factors were computed as the discrete cosine transform coefficients (DCTCs) of the magnitude spectra. The database used in these experiments consisted of 2481 CVC syllables spoken in isolation by ten males, ten females, and ten children. In all experiments, 15 speakers were used to train the classifier and the other 15 speakers were used for evaluation. For the case of dynamic features, DCTCs were computed over a 50‐ms interval beginning with the burst using 7‐ms frames spaced every 5 ms. For the static case, the DCTCs were computed from one 25.6‐ms frame beginning at the burst. Automatic classification results, based on the test data, were 87.2% for the dynamic spectral shape features versus 60.1% for the static case. Dynamic features timed to begin with the formant transition area resulted in 44.6% recognition rates. Control experiments with formants resulted in much lower recognition rates under every condition tested. In summary, these results are in agreement with the theory that dynamic spectral shape, spanning an interval of approximately 50 ms beginning at the burst, carries most of the information for initial stop consonants [D. Kewley‐Port, J. Acoust. Soc. Am. 73, 322–335 (1983)]. [Work supported by NSF.]