Text independent speaker identification using automatic acoustic segmentation
- 4 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 293-296
- https://doi.org/10.1109/icassp.1990.115638
Abstract
An acoustic-class-dependent technique for text-independent speaker identification on very short utterances is described. The technique is based on maximum-likelihood estimation of a Gaussian mixture model representation of speaker identity. Gaussian mixtures are noted for their robustness as a parametric model and their ability to form smooth estimates of rather arbitrary underlying densities. Speaker model parameters are estimated using a special case of the iterative expectation-maximization (EM) algorithm, and a number of techniques are investigated for improving model robustness. The system is evaluated using a 12 reference speaker population from a conversational speech database. It achieves 80% average text-independent speaker identification performance for a 1-s test utterance length.Keywords
This publication has 3 references indexed in Scilit:
- Investigation of text-independent speaker indentification over telephone channelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Unsupervised speaker adaptation by probabilistic spectrum fittingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Speaker recognitionIEEE ASSP Magazine, 1986