Skip to Main Content
A probabilistic vector model was developed to identify phonemically equivalent intervocalic stop consonants independently of the succeeding vowel's identity or the differences among talkers. Acoustic features of stop perception and production were studied as random processes whose probability density functions provided models for describing either the voicing mode or place-of-articulation of a stop. Each acoustic feature present in a stop's production contributed a vector whose magnitude and direction were determined from these acoustically based feature models. Combining these vectors resulted in the stop's identification. The voicing mode model performed as well as trained listeners (greater than 99% correct recognition) while the place-of-articulation model performed 15% below the level of trained listeners.