author = {St├ęphane Rossignol and Olivier Pietquin},
title = {Single-speaker/multi-speaker co-channel speech classification},
year = {2010},
booktitle = {Proceedings of the International Conference on Speech Communication and Technologies (Interspeech 2010)},
publisher = {ISCA},
pages = {2322-2325},
month = {September},
address = {Makuhari (Japan)},
url = {http://www.metz.supelec.fr//metz/personnel/pietquin/pdf/IS_2010_SROP.pdf},
abstract = {The demand for content-based management and real-time manipulation of audio data is constantly increasing. This paper presents a method to identify temporal regions, in a segment of co-channel speech, as being either single-speaker or multi- speaker speech. The state of the art approach for this purpose is the kurtosis. In this paper, a set of complementary time- domain and frequency-domain features is studied. The employed classification scheme is the one-class SVM classifier. A recognition rate of 94.75 % is reached. The set of features providing the best performance is determined.}