Speaker identification in mismatch training and testing conditions

This paper presents an exhaustive study about the robustness of several parameterizations, with a new database specially acquired for the purpose of this study. This database includes the following variations: different recording sessions (including telephonic and microphonic recordings), recording rooms, and languages (it has been obtained from a bilingual set of speakers). This study has been performed with two identification algorithms (vector quantization and covariance matrices) and reveals that the combination of several parameterizations can improve the robustness in all the scenarios.

[1]  Javier Ortega-Garcia,et al.  AHUMADA: a large speech corpus in Spanish for speaker identification and verification , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[2]  R. P. Ramachandran,et al.  Robust speaker recognition: a feature-based approach , 1996, IEEE Signal Processing Magazine.

[3]  Frank K. Soong,et al.  On the use of instantaneous and transitional spectral information in speaker recognition , 1988, IEEE Trans. Acoust. Speech Signal Process..

[4]  Biing-Hwang Juang,et al.  A vector quantization approach to speaker recognition , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Frédéric Bimbot,et al.  Text-free speaker recognition using an arithmetic-harmonic sphericity measure , 1993, EUROSPEECH.