%Aigaion2 BibTeX export from Idiap Publications
%Tuesday 03 December 2024 06:04:56 PM

@ARTICLE{Friedland_TASLP_2011,
         author = {Friedland, Gerald and Janin, Adam and Imseng, David and Anguera, Xavier and Gottlieb, Luke and Huijbregts, Marijn and Knox, Mary Tai and Vinyals, Oriol},
       projects = {Idiap, IM2, AMIDA},
          month = feb,
          title = {The ICSI RT-09 Speaker Diarization System},
        journal = {IEEE Transactions on Audio, Speech, and Language Processing},
         volume = {20},
         number = {2},
           year = {2012},
          pages = {371--381},
           issn = {1558-7916},
            doi = {10.1109/TASL.2011.2158419},
       abstract = {The speaker diarization system developed at the International Computer Science Institute (ICSI) has played a prominent role in the speaker diarization community, and many researchers in the Rich Transcription community have adopted methods and techniques developed for the ICSI speaker diarization engine. Although there have been many related publications over the years, previous articles only presented changes and improvements rather than a description of the full system. Attempting to replicate the ICSI speaker diarization system as a complete entity would require an extensive literature review, and might ultimately fail due to component description version mismatches. This article therefore presents the first full conceptual description of the ICSI speaker diarization system as presented to the National Institute of Standards Technology Rich Transcription 2009 (NIST RT-09) evaluation, which consists of online and offline subsystems, multi-stream and single-stream implementations, and audio and audio-visual approaches. Some of the components, such as the online system, have not been previously described. The article also includes all necessary preprocessing steps, such as Wiener filtering, speech activity detection and beamforming.}
}