CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
End-to-end Language Identification using Attention-based Recurrent Neural Networks
Wang Geng; Wenfu Wang; Yuanyuan Zhao; Xinyuan Cai; Bo Xu; Cai Xinyuan
Conference NameInterSpeech2016
Source PublicationInterSpeech2016
Conference Date2016.9.8-2016.9.12
Conference PlaceSan Francisco, USA
AbstractThis paper proposes a novel attention-based recurrent neural
network (RNN) to build an end-to-end automatic language identification
(LID) system. Inspired by the success of attention
mechanism on a range of sequence-to-sequence tasks, this work
introduces the attention mechanism with long short term memory
(LSTM) encoder to the sequence-to-tag LID task. This unified
architecture extends the end-to-end training method to LID
system and dramatically boosts the system performance. Firstly,
a language category embedding module is used to provide
attentional vector which guides the derivation of the utterance
level representation. Secondly, two attention approaches are explored:
a soft attention which attends all source frames and a
hard one that focuses on a subset of the sequential input. Thirdly,
a hybrid test method which traverses all gold labels is adopted
in the inference phase. Experimental results show that 8.2%
relative equal error rate (EER) reduction is obtained compared
with the LSTM-based frame level system by the soft approach
and 34.33% performance improvement is observed compared to
the conventional i-Vector system.
KeywordLanguage Identification End-to-end Training Attention
Document Type会议论文
Corresponding AuthorCai Xinyuan
Recommended Citation
GB/T 7714
Wang Geng,Wenfu Wang,Yuanyuan Zhao,et al. End-to-end Language Identification using Attention-based Recurrent Neural Networks[C],2016.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang Geng]'s Articles
[Wenfu Wang]'s Articles
[Yuanyuan Zhao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang Geng]'s Articles
[Wenfu Wang]'s Articles
[Yuanyuan Zhao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang Geng]'s Articles
[Wenfu Wang]'s Articles
[Yuanyuan Zhao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.