Achieving an accurate speaker modeling is a crucial step in any speaker-related algorithm. Many statistical speaker modeling techniques that deviate from the classical GMM/UBM approach have been proposed for some time now that can accurately discriminate between speakers. Although many of them imply the evaluation of high dimensional feature vectors and represent a speaker with a single vector, therefore not using any temporal information. In addition, they place most emphasis on modeling the most recurrent acoustic events, instead of less occurring speaker discriminant information. In this paper we explain the main benefits of our recently proposed binary speaker modeling technique and show its benefits in two particular applications, namely for speaker recognition and speaker diarization. Both applications achieve near to state-of-the-art results while benefiting from performing most processing in the binary space.
Bibliographic reference. Bonastre, Jean-François / Anguera, Xavier / Sierra, Gabriel H. / Bousquet, Pierre-Michel (2011): "Speaker modeling using local binary decisions", In INTERSPEECH-2011, 13-16.