This paper presents a unified model to perform language and speaker
recognition simultaneously and altogether. The model is based on a multi-task
recurrent neural network where the output of one task is fed as the input of
the other, leading to a collaborative learning framework that can improve both
language and speaker recognition by borrowing information from each other. Our
experiments demonstrated that the multi-task model outperforms the
task-specific models on both tasks.
Description
Collaborative Learning for Language and Speaker Recognition
%0 Generic
%1 li2016collaborative
%A Li, Lantian
%A Tang, Zhiyuan
%A Wang, Dong
%A Feng, Yang
%A Zhang, Shiyue
%D 2016
%K tag
%T Collaborative Learning for Language and Speaker Recognition
%U http://arxiv.org/abs/1609.08442
%X This paper presents a unified model to perform language and speaker
recognition simultaneously and altogether. The model is based on a multi-task
recurrent neural network where the output of one task is fed as the input of
the other, leading to a collaborative learning framework that can improve both
language and speaker recognition by borrowing information from each other. Our
experiments demonstrated that the multi-task model outperforms the
task-specific models on both tasks.
@misc{li2016collaborative,
abstract = {This paper presents a unified model to perform language and speaker
recognition simultaneously and altogether. The model is based on a multi-task
recurrent neural network where the output of one task is fed as the input of
the other, leading to a collaborative learning framework that can improve both
language and speaker recognition by borrowing information from each other. Our
experiments demonstrated that the multi-task model outperforms the
task-specific models on both tasks.},
added-at = {2017-03-12T17:04:26.000+0100},
author = {Li, Lantian and Tang, Zhiyuan and Wang, Dong and Feng, Yang and Zhang, Shiyue},
biburl = {https://www.bibsonomy.org/bibtex/2fbe413e2379b48efe7f30265e8a53772/arianepatrizia},
description = {Collaborative Learning for Language and Speaker Recognition},
interhash = {18b0d6ee66d5a3f6dd71935c6eae838a},
intrahash = {fbe413e2379b48efe7f30265e8a53772},
keywords = {tag},
note = {cite arxiv:1609.08442Comment: Submitted to ICASSP 2017},
timestamp = {2017-03-12T17:04:26.000+0100},
title = {Collaborative Learning for Language and Speaker Recognition},
url = {http://arxiv.org/abs/1609.08442},
year = 2016
}