Sixth European Conference on Speech Communication and Technology

Budapest, Hungary
September 5-9, 1999

Modeling the Rate of Speech by Markov Processes on Curves

Lawrence Saul, Mazin Rahim

AT&T Labs - Research, Florham Park, NJ, USA

We propose a statistical model for automatic speech recognition that relates variations in speaking rate to nonlinear warpings of time. The model describes a discrete random variable, s(t), that evolves as a function of the arc length traversed along a curve, parameterized by x(t). Since arc length does not depend on the rate at which a curve is traversed, this evolution gives rise to a family of Markov processes whose predictions, Pr[s|x], are invariant to nonlinear warpings of time. We describe the use of such models, known as Markov processes on curves (MPCs), for automatic speech recognition, where x are acoustic feature trajectories and s are phonetic transcriptions. On two tasks|recognizing New Jersey town names and connected alpha-digits|we find that MPCs yield lower word error rates than comparably trained hidden Markov models.

Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Saul, Lawrence / Rahim, Mazin (1999): "Modeling the rate of speech by Markov processes on curves", In EUROSPEECH'99, 415-418.