Automatic speech recognition fusion approach to unsupervised speaker clustering and labeling

This paper describes a fully unsupervised approach to speaker clustering and labeling employing speech recognition (ASR) technology to bootstrap speaker identification (SID). An algorithm that combined these two technologies was able to correctly cluster and label 299 NATO ship-to-ship transmissions...

Full description

Saved in:
Bibliographic Details
Main Authors: Lawson, A.D., Huggins, M.C., Grieco, J.J., Galligan, S.A., Harris, D.M.
Format: Conference Proceeding
Language:English
Subjects:
Automatic speech recognition
Clustering algorithms
Humans
Labeling
Laboratories
Natural languages
Speaker recognition
Speech processing
Speech recognition
USA Councils
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper describes a fully unsupervised approach to speaker clustering and labeling employing speech recognition (ASR) technology to bootstrap speaker identification (SID). An algorithm that combined these two technologies was able to correctly cluster and label 299 NATO ship-to-ship transmissions with an accuracy of 89% in an on-line (no a priori training) scenario. This fusion approach out-performed ASR alone by 23.6%, and outperformed manually-trained VQ-SID by 12.7% and GMM/UMB-SID by 8.6%. This paper demonstrates that, under certain circumstances, unsupervised, self-organizing systems can be more effective than manually-trained ones
ISSN:1095-323X
2996-2358
DOI:10.1109/AERO.2006.1656042