In this paper, we examine the use of Joint Factor Analysis methods on RSR2015 digits. A tied-mixture model is used for segmentation of the utterances into digits, while Joint Factor Analysis and a Joint Density model are deployed for features and backend, respectively. A novel approach for digit-dependent fusion of UBM-component log-likelihood ratios is introduced, yielding the best results so far. The fusion of 5 different JFA features gives an equal-error rate of 3.6%, compared to 6.3% attained by the a baseline GMM-UBM model with score normalization.
Cite as: Stafylakis, T., Kenny, P., Alam, M.J., Kockmann, M. (2015) JFA for speaker recognition with random digit strings. Proc. Interspeech 2015, 190-194, doi: 10.21437/Interspeech.2015-82
@inproceedings{stafylakis15_interspeech,
author={Themos Stafylakis and Patrick Kenny and Md. Jahangir Alam and Marcel Kockmann},
title={{JFA for speaker recognition with random digit strings}},
year=2015,
booktitle={Proc. Interspeech 2015},
pages={190--194},
doi={10.21437/Interspeech.2015-82}
}