Improved Weighted Matching for Speaker Recognition

Authors: Ozan Mut, Mehmet Göktürk

Abstract:

Matching algorithms have significant importance in speaker recognition. Feature vectors of the unknown utterance are compared to feature vectors of the modeled speakers as a last step in speaker recognition. A similarity score is found for every model in the speaker database. Depending on the type of speaker recognition, these scores are used to determine the author of unknown speech samples. For speaker verification, similarity score is tested against a predefined threshold and either acceptance or rejection result is obtained. In the case of speaker identification, the result depends on whether the identification is open set or closed set. In closed set identification, the model that yields the best similarity score is accepted. In open set identification, the best score is tested against a threshold, so there is one more possible output satisfying the condition that the speaker is not one of the registered speakers in existing database. This paper focuses on closed set speaker identification using a modified version of a well known matching algorithm. The results of new matching algorithm indicated better performance on YOHO international speaker recognition database.

Keywords: Automatic Speaker Recognition, Voice Recognition, Pattern Recognition, Digital Audio Signal Processing.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1076518

References:

[1] T. Kinnunen and P. Fränti, "Speaker Discriminative Weighting Method for VQ-Based Speaker Identification", Proc. 3rd International Conference on audio and video-based biometric person authentication (AVBPA)), Halmstad, Sweden, 2001.
[2] T. Kinnunen and P. Fränti, " Spectral Features for Automatic Text- Independent Speaker Recognition" Licentiate-s Thesis. http://www.cs.joensuu.fi/pages/pums/public_results/2004_PhLic_Kinnu nen_Tomi.pdf
[3] Campbell, J. JR. Senior Member, IEEE Speaker recognition: a tutorial. Invited Paper
[4] Evgeny Karpov,.Real-Time Speaker Identification. 15.01.2003. University of Joensuu. Department of Computer Science. Master-s Thesis