Impact of overlapping speech detection on speaker diarization for broadcast news and debates

The overlapping speech detection systems developped by Orange and LIMSI for the ETAPE evaluation campaign on French broadcast news and debates are described. Using either cepstral features or a multi-pitch analysis, a F1-measure for overlapping speech detection up to 59.2% is reported on the TV data...

Full description

Saved in:
Bibliographic Details
Main Authors: Charlet, Delphine, Barras, Claude, Lienard, Jean-Sylvain
Format: Conference Proceeding
Language:English
Subjects:
Abstracts
Acoustics
Density estimation robust algorithm
overlapping speech
speaker diarization
Speech
Speech recognition
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The overlapping speech detection systems developped by Orange and LIMSI for the ETAPE evaluation campaign on French broadcast news and debates are described. Using either cepstral features or a multi-pitch analysis, a F1-measure for overlapping speech detection up to 59.2% is reported on the TV data of the ETAPE evaluation set, where 6.7% of the speech was measured as overlapping, ranging from 1.2% in the news to 10.4% in the debates. Overlapping speech segments were excluded during the speaker diarization stage, and these segments were further labelled with the two nearest speaker labels, taking into account the temporal distance. We describe the effects of this strategy for various overlapping speech systems and we show that it improves the diarization error rate in all situations and up to 26.1% relative in our best configuration.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2013.6639163