Fourth European Conference on Speech Communication and Technology

Madrid, Spain
September 18-21, 1995

A Competitive Algorithm for Training HMM for Speech Recognition

Pedro L. Galindo

Universidad de Cadiz, C/ Chile S/N, Cadiz, Spain

In this paper we describe an alternative estimation procedure for training Hidden Markov Models (HMM) called Competitive Forward-Backward (CFB) algorithm, which is aimed at minimizing the number of recognition errors. CFB integrates the LVQ3 neural network classification technique into the Baum-Welch training algorithm, and improves significantly the performance of HMM systems over previously reported procedures, such as Baum-Welch and Corrective Training.

Full Paper

Bibliographic reference.  Galindo, Pedro L. (1995): "A competitive algorithm for training HMM for speech recognition", In EUROSPEECH-1995, 2187-2190.