Single-speaker/multi-speaker co-channel speech classification - CentraleSupélec Access content directly
Conference Papers Year : 2010

Single-speaker/multi-speaker co-channel speech classification

Stéphane Rossignol
Olivier Pietquin


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.


Sound [cs.SD]
No file

Dates and versions

hal-00552948 , version 1 (06-01-2011)


  • HAL Id : hal-00552948 , version 1


Stéphane Rossignol, Olivier Pietquin. Single-speaker/multi-speaker co-channel speech classification. Interspeech 2010, Sep 2010, Makuhari, Japan. pp.2322-2325. ⟨hal-00552948⟩
32 View
0 Download


Gmail Mastodon Facebook X LinkedIn More