The SuperSID project: exploiting high-level information for high-accuracy speaker recognition
Lists
Only you see this
Abstract
The area of automatic speaker recognition has been dominated by systems using only short-term, low-level acoustic information, such as cepstral features. While these systems have indeed produced very low error rates, they ignore other levels of information beyond low-level acoustics that convey speaker information. Recently published work has shown examples that such high-level information can be used successfully in automatic speaker recognition systems and has the potential to improve accuracy and add robustness. For the 2002 JHU CLSP summer workshop, the SuperSID project (http://www.clsp.jhu.edu/ws2002/groups/supersid/) was undertaken to exploit these high-level information sources and dramatically increase speaker recognition accuracy on a defined NIST evaluation corpus and task. The paper provides an overview of the structure, data, task, tools, and accomplishments of this project. Wide ranging approaches using pronunciation models, prosodic dynamics, pitch and duration features, phone streams, and conversational interactions were explored and developed. We show how these novel features and classifiers indeed provide complementary information and can be fused together to drive down the equal error rate on the 2001 NIST extended data task to 0.2% - a 71% relative reduction in error over the previous state of the art.
BibTeX
@inproceedings{reynolds2003supersid,
author = {Douglas A. Reynolds and Walter D. Andrews and Joseph P. Campbell and Jirí Navrátil and Barbara Peskin and André Adami and Qin Jin and David Klusácek and Joy S. Abramson and Radu Mihaescu and John J. Godfrey and Douglas A. Jones and Bing Xiang},
title = {{The SuperSID project: exploiting high-level information for high-accuracy speaker recognition}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2003},
doi = {10.1109/icassp.2003.1202760},
}Loading related content...