Speech overlap detection and attribution using convolutive non-negative sparse coding

Overlapping speech is known to degrade speaker diarization performance with impacts on speaker clustering and segmentation. While previous work made important advances in detecting overlapping speech intervals and in attributing them to relevant speakers, the problem remains largely unsolved. This p...

Full description

Saved in:
Bibliographic Details
Published in:2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 4181 - 4184
Main Authors: Vipperla, R., Geiger, J. T., Bozonnet, S., Dong Wang, Evans, N., Schuller, B., Rigoll, G.
Format: Conference Proceeding
Language:English
Published: IEEE 01.03.2012
Subjects:
convolutive non-negative sparse coding
Density estimation robust algorithm
Encoding
Error analysis
Hidden Markov models
Matrix decomposition
overlap detection
Sparse matrices
speaker attribution
speaker diarization
Speech
ISBN:1467300454, 9781467300452
ISSN:1520-6149
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Overlapping speech is known to degrade speaker diarization performance with impacts on speaker clustering and segmentation. While previous work made important advances in detecting overlapping speech intervals and in attributing them to relevant speakers, the problem remains largely unsolved. This paper reports the first application of convolutive non-negative sparse coding (CNSC) to the overlap problem. CNSC aims to decompose a composite signal into its underlying contributory parts and is thus naturally suited to overlap detection and attribution. Experimental results on NIST RT data show that the CNSC approach gives comparable results to a state-of-the-art hidden Markov model based overlap detector. In a practical diarization system, CNSC based speaker attribution is shown to reduce the speaker error by over 40% relative in overlapping segments.
ISBN:1467300454
9781467300452
ISSN:1520-6149
DOI:10.1109/ICASSP.2012.6288840