Multi-domain language recognition involves the application of a language identification (LID) system to identify languages in more than one domain. This problem was the focus of the recent NIST LRE 2017, and this article presents the findings from the SRI team during system development for the evaluation. Approaches found to provide robustness in multi-domain LID include a domain-and-language-weighted Gaussian backend classifier, duration-aware calibration, and a source normalized multi-resolution neural network backend. The recently developed speaker embeddings technology is also applied to the task of language recognition, showing great potential for future LID research.
Cite as: Mclaren, M., Nandwana, M.K., Castán, D., Ferrer, L. (2018) Approaches to Multi-domain Language Recognition. Proc. The Speaker and Language Recognition Workshop (Odyssey 2018), 90-97, doi: 10.21437/Odyssey.2018-13
@inproceedings{mclaren18b_odyssey,
author={Mitchell Mclaren and Mahesh Kumar Nandwana and Diego Castán and Luciana Ferrer},
title={{Approaches to Multi-domain Language Recognition}},
year=2018,
booktitle={Proc. The Speaker and Language Recognition Workshop (Odyssey 2018)},
pages={90--97},
doi={10.21437/Odyssey.2018-13}
}