Robust speaker identification based on selective use of feature vectors

Authors:
Soonil Kwon;Shrikanth Narayanan
Affiliations:
System Technology Division, Korea Institute of Science and Technology, Seoul 130-650, Korea;Department of Electrical Engineering and IMSC, University of Southern California, Los Angeles, CA 90089, United States
Venue:
Pattern Recognition Letters
Year:
2007

Citing 1
Cited 1

Multimodal people ID for a multimedia meeting browser

MULTIMEDIA '99 Proceedings of the seventh ACM international conference on Multimedia (Part 1)

Speaker segmentation for intelligent responsive space

HCI'07 Proceedings of the 12th international conference on Human-computer interaction: intelligent multimodal interaction environments

Quantified Score

Hi-index	0.10

Visualization

Abstract

A new method for speaker identification that selectively uses feature vectors for robust decision-making is described. Experimental results, with short speech segments ranging from 0.25 to 2s, showed that our method consistently outperforms other approaches yielding relative improvements of 20-51% and 15-30% over baseline GMM and the LDA-GMM systems, respectively.