%Aigaion2 BibTeX export from Idiap Publications
%Sunday 22 December 2024 02:38:47 AM

@INPROCEEDINGS{Vijayasenan_INTERSPEEH2009_2009,
         author = {Vijayasenan, Deepu and Valente, Fabio and Bourlard, Herv{\'{e}}},
       projects = {Idiap, AMIDA, IM2},
          title = {KL Realignment for Speaker Diarization with Multiple Feature Streams},
      booktitle = {10th Annual Conference of the International Speech Communication Association},
           year = {2009},
       crossref = {Vijayasenan_Idiap-RR-24-2010},
       abstract = {This paper aims at investigating the use of Kullback-Leibler (KL) divergence based realignment with application to speaker diarization. The use of KL divergence based realignment operates directly on the speaker posterior distribution estimates and is compared with traditional realignment performed using HMM/GMM system. We hypothesize that using posterior estimates to re-align speaker boundaries is more robust than gaussian mixture models in case of multiple feature streams with different statistical properties. Experiments are run on the NIST RT06 data. These experiments reveal that in case of conventional MFCC features the two approaches yields the same performance while the KL based system outperforms the HMM/GMM re-alignment in case of combination of multiple feature streams (MFCC and TDOA).}
}



crossreferenced publications: 
@TECHREPORT{Vijayasenan_Idiap-RR-24-2010,
         author = {Vijayasenan, Deepu and Valente, Fabio and Bourlard, Herv{\'{e}}},
       projects = {Idiap, AMIDA, IM2},
          month = {7},
          title = {KL Realignment for Speaker Diarization with Multiple Feature Streams},
           type = {Idiap-RR},
         number = {Idiap-RR-24-2010},
           year = {2010},
    institution = {Idiap},
       abstract = {This paper aims at investigating the use of Kullback-Leibler (KL) divergence based realignment with application to speaker diarization. The use of KL divergence based realignment operates directly on the speaker posterior distribution estimates and is compared with traditional realignment performed using HMM/GMM system. We hypothesize that using posterior estimates to re-align speaker boundaries is more robust than gaussian mixture models in case of multiple feature streams with different statistical properties. Experiments are run on the NIST RT06 data. These experiments reveal that in case of conventional MFCC features the two approaches yields the same performance while the KL based system outperforms the HMM/GMM re-alignment in case of combination of multiple feature streams (MFCC and TDOA).},
            pdf = {https://publications.idiap.ch/attachments/reports/2009/Vijayasenan_Idiap-RR-24-2010.pdf}
}