The paper describes a structural framework for the design of a speaker recognition system based on multiple models. This combination is not only at the recognition level, but also at a joint training of the models. This unified training of the models uses a common structure : a decomposition tree of the set of data of normalization speakers. For the experiments, the Gaussian Mixture Model and the Auto-Regressive Vectorial Model are the two models we have selected to test the structural framework of the speaker verification scoring combination. This approach has been tested on a subset of the 30"-NIST97 Speaker Recognition Evaluation corpus. The list of the files of this subset (i.e., normalization, training and test) can be found at http://www-apa.lip6.fr/PAROLE/ICSLP2000/.
Cite as: Montacié, C., Caraty, M.-J. (2000) Structural framework for combining speaker recognition methods. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 2, 479-482, doi: 10.21437/ICSLP.2000-311
@inproceedings{montacie00_icslp,
author={Claude Montacié and Marie-José Caraty},
title={{Structural framework for combining speaker recognition methods}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 2, 479-482},
doi={10.21437/ICSLP.2000-311}
}