%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 06:10:26 PM

@ARTICLE{Vijayasenan_TASL_2011,
         author = {Vijayasenan, Deepu and Valente, Fabio and Bourlard, Herv{\'{e}}},
       projects = {Idiap, SNSF-MULTI, AMIDA},
          month = {2},
          title = {An Information Theoretic Combination of MFCC and TDOA Features for Speaker Diarization},
        journal = {IEEE Transactions on Audio Speech and Language Processing},
         volume = {19},
         number = {2},
           year = {2011},
            doi = {10.1109/TASL.2010.2048603},
       crossref = {Vijayasenan_Idiap-RR-22-2010},
       abstract = {This correspondence describes a novel system for speaker diarization of meetings recordings based on the combination of acoustic features (MFCC) and time delay of arrivals (TDOAS). The first part of the paper analyzes differences between MFCC and TDOA features which possess completely different statistical properties. When Gaussian mixture models are used, experiments reveal that the diarization system is sensitive to the different recording scenarios (i.e., meeting rooms with varying number of microphones). In the second part, a new multistream diarization system is proposed extending previous work on information theoretic diarization. Both speaker clustering and speaker realignment steps are discussed; in contrary to current systems, the proposed method avoids to perform the feature combination averaging log-likelihood scores. Experiments on meetings data reveal that the proposed approach outperforms the GMM-based system when the recording is done with varying number of microphones.}
}



crossreferenced publications: 
@TECHREPORT{Vijayasenan_Idiap-RR-22-2010,
         author = {Vijayasenan, Deepu and Valente, Fabio and Bourlard, Herv{\'{e}}},
       projects = {Idiap, SNSF-MULTI, IM2},
          month = {7},
          title = {An Information Theoretic Combination of MFCC and TDOA Features for Speaker Diarization},
           type = {Idiap-RR},
         number = {Idiap-RR-22-2010},
           year = {2010},
    institution = {Idiap},
       abstract = {This work describes a novel system for speaker
diarization of meetings recordings based on the combination of acoustic
features (MFCC) and Time Delay of Arrivals (TDOA). The first part
of the paper analyzes differences between MFCC and TDOA features
which possess completely different statistical properties. When Gaussian
Mixture Models are used, experiments reveal that the diarization system
is sensitive to the different recording scenarios (i.e. meeting rooms with
varying number of microphones). In the second part, a new multistream
diarization system is proposed extending previous work on Information
Theoretic diarization. Both speaker clustering and speaker realignment
steps are discussed; in contrary to current systems, the proposed method
avoids to perform the feature combination averaging log-likelihood
scores. Experiments on meetings data reveal that the proposed approach
outperforms the GMM based system when the recording is done with
varying number of microphones.},
            pdf = {https://publications.idiap.ch/attachments/reports/2010/Vijayasenan_Idiap-RR-22-2010.pdf}
}