End-to-end Language Identification using Attention-based Recurrent Neural Networks
Wang Geng; Wenfu Wang; Yuanyuan Zhao; Xinyuan Cai; Bo Xu; Cai Xinyuan
2016-09
会议名称InterSpeech2016
会议录名称InterSpeech2016
会议日期2016.9.8-2016.9.12
会议地点San Francisco, USA
摘要This 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.
关键词Language Identification End-to-end Training Attention
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12483
专题数字内容技术与服务研究中心_听觉模型与认知计算
通讯作者Cai Xinyuan
作者单位Institute of Automation Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Wang Geng,Wenfu Wang,Yuanyuan Zhao,et al. End-to-end Language Identification using Attention-based Recurrent Neural Networks[C],2016.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
End-to-end Language (610KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang Geng]的文章
[Wenfu Wang]的文章
[Yuanyuan Zhao]的文章
百度学术
百度学术中相似的文章
[Wang Geng]的文章
[Wenfu Wang]的文章
[Yuanyuan Zhao]的文章
必应学术
必应学术中相似的文章
[Wang Geng]的文章
[Wenfu Wang]的文章
[Yuanyuan Zhao]的文章
相关权益政策
暂无数据
收藏/分享
文件名: End-to-end Language Identification using Attention-based Recurrent Neural Networks.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。