@inproceedings{9329da2d5cb9498e9ff8dd360e0b37bd,
title = "Speech overlap detection and attribution using convolutive non-negative sparse coding",
abstract = "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.",
keywords = "convolutive non-negative sparse coding, overlap detection, speaker attribution, speaker diarization",
author = "Ravichander Vipperla and Geiger, {J{\"u}rgen T.} and Simon Bozonnet and Dong Wang and Nicholas Evans and Bj{\"o}rn Schuller and Gerhard Rigoll",
year = "2012",
doi = "10.1109/ICASSP.2012.6288840",
language = "English",
isbn = "9781467300469",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
pages = "4181--4184",
booktitle = "2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings",
note = "2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 ; Conference date: 25-03-2012 Through 30-03-2012",
}