5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

The Voicing Feature for Stop Consonants: Acoustic Phonetic Analyses and Automatic Speech Recognition Experiments

Padma Ramesh, Partha Niyogi

Bell Labs - Lucent Technologies, USA

We examine the distinctive feature [voice] that separates the voiced from the unvoiced sounds for the case of stop consonants. We conduct acoustic phonetic analyses on a large database and demonstrate the superior separability using a temporal measure (voice onset time; VOT) rather than spectral measures. We describe several algorithms to automatically estimate the VOT from continuous speech and compare them on a speech recognition problem to reduce error rates by as much as 53 percent over a baseline HMM based system.

Full Paper

Bibliographic reference.  Ramesh, Padma / Niyogi, Partha (1998): "The voicing feature for stop consonants: acoustic phonetic analyses and automatic speech recognition experiments", In ICSLP-1998, paper 0881.