Gating Recurrent Enhanced Memory Neural Networks on Language Identification

	Gating Recurrent Enhanced Memory Neural Networks on Language Identification
	Wang Geng; Yuanyan Zhao; Wenfu Wang; Cai Xinyuan; Bo Xu; Xinyuan Cai
	2016-09
会议名称	InterSpeech2016
会议录名称	InterSpeech 2016
会议日期	2016.9.8-2016.9.12
会议地点	San Francisco, USA
摘要	This paper proposes a novel memory neural network structure, namely gating recurrent enhanced memory network (GREMN), to model long-range dependency in temporal series on language identification (LID) task at the acoustic frame level. The proposed GREMN is a stacking gating recurrent neural network (RNN) equipped with a learnable enhanced memory block near the classifier. It aims at capturing the long-span history and certain future contextual information of the sequential input. In addition, two optimization strategies of coherent SortaGrad-like training mechanism and a hard sample score acquisition approach are proposed. The proposed optimization policies drastically boost this memory network based LID system, especially on the large disparity training materials. It is confirmed by the experimental results that the proposed GREMN possesses strong ability of sequential modeling and generalization, where about 5% relative equal error rate (EER) reduction is obtained comparing with the approximate-sized gating RNNs and 38.5% performance improvements is observed compared to conventional i-Vector based LID system.
关键词	Language Identification Gating Recurrent Neural Networks Learnable Enhanced Memory Block Sortagrad-like Training Approach Hard Sample Score Acquisition
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/41094
专题	复杂系统认知与决策实验室_听觉模型与认知计算
通讯作者	Xinyuan Cai
推荐引用方式 GB/T 7714	Wang Geng,Yuanyan Zhao,Wenfu Wang,et al. Gating Recurrent Enhanced Memory Neural Networks on Language Identification[C],2016.