ASA 130th Meeting - St. Louis, MO - 1995 Nov 27 .. Dec 01

4pSC10. Vowel recognition using an articulatory representation.

G. Richard

Q. Lin

F. Zussa

D. Sinder

C. Che

J. Flanagan

Rutgers Univ.-CAIP Ctr., Piscataway, NJ 08855-1390

An alternate approach to speech recognition based on an articulatory representation of speech is proposed. Unlike traditional methods based on Fourier or cepstrum representations, the articulatory description of speech provides a compact parametrization linked to physiological properties. The expected results are robust speaker-independent speech recognition. In fact, physiologically related parameters should be useful for handling variability across speakers. In this work, a three-parameter articulatory representation is applied to vowel recognition. These parameters (location and size of the main constriction in the vocal tract and the ratio of lip length to mouth aperture) are estimated using a codebook search strategy. Before the recognition process, a pattern database is built using a corpus of ten repetitions of nine different vowels. Vector quantization is then applied to this corpus to obtain several representative articulatory vectors, or centroids, for each vowel. In the recognition stage, articulatory parameters of the incoming speech segments are estimated and compared to the centroids of the pattern database to arrive at a recognition decision. Initial results indicate strong potential for articulatory-based speech recognition. [Research supported by ARPA-DAST 63-93-C-0064.]