End-to-end Language Identification using Attention-based Recurrent Neural Networks

CORC > 自动化研究所 > 中国科学院自动化研究所 > 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
	2016-09
会议日期	2016.9.8-2016.9.12
会议地点	San Francisco, USA
关键词	Language Identification End-to-end Training Attention
英文摘要	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.
会议录	InterSpeech2016
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/41097]
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
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]. 见:. San Francisco, USA. 2016.9.8-2016.9.12.