Speaker Identification Using Autoregressive Hidden Markov Models and Adaptive Vector Quantisation

Authors:
Eugeny E. Bovbel;Igor E. Kheidorov;Michael E. Kotlyar
Affiliations:
-;-;-
Venue:
TDS '00 Proceedings of the Third International Workshop on Text, Speech and Dialogue
Year:
2000

Citing 2
Cited 0

Speaker identification and verification using Gaussian mixture speaker models

Speech Communication
Connectionist Speech Recognition: A Hybrid Approach

Connectionist Speech Recognition: A Hybrid Approach

Quantified Score

Hi-index	0.02

Visualization

Abstract

Wide-frequency spectral analysis, autoregressive hidden Markov models (ARHMM)and self-organising neural networks (SOM) have been used for high accuracy speaker features modelling. The initial ARHMM parameters estimation based on Kalman filter is proposed. The five-keyword speaker identification system has been built and tested. The experiments show that this approach provides high accuracy of speaker identification even if the same words are pronounced by different speakers.