CONF Imseng_ASRU_2009/IDIAP Robust Speaker Diarization for Short Speech Recordings Imseng, David Friedland, Gerald EXTERNAL https://publications.idiap.ch/attachments/papers/2009/Imseng_ASRU_2009.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/Imseng_Idiap-RR-26-2009 Related documents Proceedings of the IEEE workshop on Automatic Speech Recognition and Understanding Merano, Italy 2009 December 2009 432-437 We investigate a state-of-the-art Speaker Diarization system regarding its behavior on meetings that are much shorter (from 500 seconds down to 100 seconds) than those typically analyzed in Speaker Diarization benchmarks. First, the problems inherent to this task are analyzed. Then, we propose an approach that consists of a novel initialization parameter estimation method for typical state-of-the-art diarization approaches. The estimation method balances the relationship between the optimal value of the duration of speech data per Gaussian and the duration of the speech data, which is verified experimentally for the first time in this article. As a result, the Diarization Error Rate for short meetings extracted from the 2006, 2007, and 2009 NIST RT evaluation data is decreased by up to 50% relative. REPORT Imseng_Idiap-RR-26-2009/IDIAP Robust Speaker Diarization for Short Speech Recordings Imseng, David Friedland, Gerald EXTERNAL https://publications.idiap.ch/attachments/reports/2009/Imseng_Idiap-RR-26-2009.pdf PUBLIC Idiap-RR-26-2009 2009 Idiap PO Box 592 CH - 1920 Martigny September 2009 We investigate a state-of-the-art Speaker Diarization system regarding its behavior on meetings that are much shorter (from 500 seconds down to 100 seconds) than those typically analyzed in Speaker Diarization benchmarks. First, the problems inherent to this task are analyzed. Then, we propose an approach that consists of a novel initialization parameter estimation method for typical state-of-the-art diarization approaches. The estimation method balances the relationship between the optimal value of the duration of speech data per Gaussian and the duration of the speech data, which is verified experimentally for the first time in this article. As a result, the Diarization Error Rate for short meetings extracted from the 2006, 2007, and 2009 NIST RT evaluation data is decreased by up to 50 % relative.