We describe a new approach for segment-based speaker recognition, given text-independent training and test data. We assume that utterances from the same speaker have more and longer matching acoustic segments, compared to utterances from different speakers. Therefore, we identify the longest matching segments, at each frame location, between the training and test utterances, and base recognition on the similarity of these longest matching segments. The new system scores the speaker higher who has greater number, length and similarity of matching segments. Focusing on long acoustic segments effectively exploits the spectral dynamics. We have compared our new system with the conventional frame-based GMM-UBM system for the NIST 2002 SRE task, and achieved better performance.
Bibliographic reference. Jafari, Ayeh / Srinivasan, Ramji / Crookes, Danny / Ming, Ji (2010): "A longest matching segment approach for text-independent speaker recognition", In INTERSPEECH-2010, 1469-1472.