A comparative study of several parameterizations for speaker recognition
This is an incremental study that addresses robustness issues in speaker recognition for applications like security or voice-based systems.
The paper tackled the problem of speaker recognition robustness under mismatch conditions by comparing multiple parameterizations, finding that combining them improved performance across all scenarios for both verification and identification tasks.
This paper presents an exhaustive study about the robustness of several parameterizations, in speaker verification and identification tasks. We have studied several mismatch conditions: different recording sessions, microphones, and different languages (it has been obtained from a bilingual set of speakers). This study reveals that the combination of several parameterizations can improve the robustness in all the scenarios for both tasks, identification and verification. In addition, two different methods have been evaluated: vector quantization, and covariance matrices with an arithmetic-harmonic sphericity measure.