论文信息 - Distributed speaker recognition using the ETSI AURORA standard

Distributed speaker recognition using the ETSI AURORA standard

The ETSI “Aurora” is a standard for distributed speech recognition over the mobile cellular network. We have investigated the use of the features defined in this standard for speaker recognition, in a text-independent system based on Gaussian Mixture Models (GMM). The application context is distributed speaker recognition for user authentication on the mobile cellular network. We have found that the use of the Aurora parameters would improve the performance compared with the existing alternative which is performing speaker recognition on GSM coded speech.

[1] Fausto Pellandini,et al. Influence of GSM speech coding on the performance of text-independent speaker recognition , 2000, 2000 10th European Signal Processing Conference.

[2] Darren Pearce,et al. Enabling new speech driven services for mobile devices: An overview of the ETSI standards activities , 2000 .

[3] C. Broun,et al. Distributed speaker recognition using the ETSI distributed speech recognition standard , 2001 .

[4] Jr. J.P. Campbell,et al. Speaker recognition: a tutorial , 1997, Proc. IEEE.

[5] 01 New Aurora Activity for Standardization of a Front-End Extension for Tonal Language Recognition and Speech Reconstruction , 2001 .

[6] F. Bimbot,et al. Second-order statistical measures for text-independent speaker identification , 1995, Speech Commun..

[7] Douglas A. Reynolds,et al. Speaker identification and verification using Gaussian mixture speaker models , 1995, Speech Commun..