Title :
I-vectors in the context of phonetically-constrained short utterances for speaker verification
Author :
Larcher, Anthony ; Bousquet, Pierre-Michel ; Lee, Kong Aik ; Matrouf, Driss ; Li, Haizhou ; Bonastre, Jean-Francois
Author_Institution :
Human Language Technol. Dept., A*STAR, Singapore, Singapore
Abstract :
Short speech duration remains a critical factor of performance degradation when deploying a speaker verification system. To overcome this difficulty, a large number of commercial applications impose the use of fixed pass-phrases. In this context, we show that the performance of the popular i-vector approach can be greatly improved by taking advantage of the phonetic information that they convey. Moreover, as i-vectors require a conditioning process to reach high accuracy, we show that further improvements are possible by taking advantage of this phonetic information within the normalisation process. We compare two methods, Within Class Covariance Normalization (WCCN) and Eigen Factor Radial (EFR), both relying on parameters estimated on the same development data. Our study suggests that WCCN is more robust to data mismatch but less efficient than EFR when the development data has a better match with the test data.
Keywords :
eigenvalues and eigenfunctions; speaker recognition; EFR; WCCN; conditioning process; eigen factor radial; i-vector approach; phonetically-constrained short utterances; speaker verification system; within class covariance normalization process; Context; Covariance matrix; Databases; Robustness; Speaker recognition; Speech; Training; Phonetic constraint; Speaker verification; i-vector; short duration;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4673-0045-2
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2012.6288986