Segmental GPD training of HMM based speech recognizer
Authors:
- 1 January 1992
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149) , 473-476 vol.1
Abstract
A novel training algorithm, segmental GPD (generalized probabilistic descent) training, for a hidden Markov model (HMM)-based speech recognizer using Viterbi decoding is proposed. This algorithm is based on the principle of minimum recognition error rate in which segmentation and discriminative training are jointly optimized. Various issues related to the special structure of HMM in segmental GPD training are studied. The authors tested this algorithm on two speaker-independent recognition tasks. The first experiment involves English E-set. Segmental GPD training was directly applied to HMM generated from nonoptimal uniform segmentation. A recognition rate of 88.7% was achieved on English E-set with whole word HMM. The second experiment involves the connected digits TI-database. Segmental GPD training was applied to HMM which were already trained using conventional training methods. A string recognition rate of 98.8% was achieved on 10-state word based HMM through segmental GPD training.<>Keywords
This publication has 4 references indexed in Scilit:
- Discriminative analysis of distortion sequences in speech recognitionIEEE Transactions on Speech and Audio Processing, 1993
- Corrective and reinforcement learning for speaker-independent continuous speech recognitionComputer Speech & Language, 1990
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989
- Recognition of Isolated Digits Using Hidden Markov Models With Continuous Mixture DensitiesAT&T Technical Journal, 1985