Temporal decomposition for the initialization of a HMM isolated word-recognizer

Authors:
M. Taylor;F. Bimbot
Affiliations:
Télécom Paris, Dept Signal, C.N.R.S., URA, Paris Cedex 13, France;Télécom Paris, Dept Signal, C.N.R.S., URA, Paris Cedex 13, France
Venue:
ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
Year:
1992

Citing 1
Cited 1

Mathematical foundations of hidden Markov models

Proceedings of the NATO Advanced Study Institute on Recent advances in speech understanding and dialog systems

Utilizing intelligent segmentation in isolated word recognition using a hybrid HTD-HMM

CISST '11 Proceedings of the 5th WSEAS international conference on Circuits, systems, signal and telecommunications

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, the technique of temporal decomposition is used to initialize continuous density Hidden Markov Models. The temporal decomposition process produces a representation of each word in terms of a set of target vectors and interpolation functions. Roughly speaking, the target vectors represent the centres of the important acoustic events, and the interpolation functions describe a spectral path between these events [1]. In our approach, the number of targets generated by the temporal decomposition process is taken to be the number of states used for the HMM, and the position, shape and length of the interpolation functions are used to provide initial estimates for the transtition probabilities and observation probability densities of the HMM. The performance of such a system is assessed for a single-speaker environment.