Simultaneous speech in meeting environment is responsible
for a certain amount of errors caused by standard speaker
diarization systems. We are presenting an overlap detection
system for far-field data based on spectral and spatial features,
where the spatial features obtained on different microphone
pairs are fused by means of principal component analysis. Detected
overlap segments are applied for speaker diarization in
order to increase the purity of speaker clusters and to recover
missed speech by assigning multiple speaker labels. Investigation
on the relationship between overlap detection properties
and diarization improvement revealed very distinct behaviour
of overlap exclusion and overlap labeling.
CitationZelenák, M.; Hernando, J. On the improvement of speaker diarization by detecting overlapped speech. A: Jornadas en Tecnología del Habla and Iberian SLTech Workshop. "VI Jornadas en Tecnología del Habla and II Iberian SLTech Workshop". 2010, p. 153-156.
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder. If you wish to make any use of the work not provided for in the law, please contact: firstname.lastname@example.org