@inproceedings{fcd40c76b5244f209c8b63a0c90f038d,
title = "Collaborative learning for language and speaker recognition",
abstract = "This paper presents a unified model to perform language and speaker recognition simultaneously and together. This model is based on a multi-task recurrent neural network, where the output of one task is fed in as the input of the other, leading to a collaborative learning framework that can improve both language and speaker recognition by sharing information between the tasks. The preliminary experiments presented in this paper demonstrate that the multi-task model outperforms similar task-specific models on both language and speaker tasks. The language recognition improvement is especially remarkable, which we believe is due to the speaker normalization effect caused by using the information from the speaker recognition component.",
author = "Lantian Li and Zhiyuan Tang and Dong Wang and Andrew Abel and Yang Feng and Shiyue Zhang",
note = "Publisher Copyright: {\textcopyright} 2018, Springer Nature Singapore Pte Ltd.; 14th National Conference on Man-Machine Speech Communication, NCMMSC 2017 ; Conference date: 11-10-2017 Through 13-10-2017",
year = "2018",
doi = "10.1007/978-981-10-8111-8_6",
language = "English",
isbn = "9789811081101",
series = "Communications in Computer and Information Science",
publisher = "Springer Verlag",
pages = "58--69",
editor = "Ya Li and Zheng, {Thomas Fang} and Changchun Bao and Dong Wang and Jianhua Tao",
booktitle = "Man-Machine Speech Communication - 14th National Conference, NCMMSC 2017, Revised Selected Papers",
}