Investigating Gated Recurrent Neural Networks for Acoustic Modeling
Zhao, Yuanyuan; Li, Jie; Xu, Shuang; Xu, Bo; Yuanyuan Zhao
2016-10
会议名称ISCSLP2016
会议日期October 17-20
会议地点Tianjin, China
摘要Recurrent neural networks (RNNs) with a gating mechanism have been shown to give state-of-the-art performance in acoustic modeling, such as gated recurrent unit (GRU), long short-term memory (LSTM), long short-term memory projected (LSTMP), etc. But little is known about why these gated RNNs work and what the differences are among these networks. Based on a series of experimental comparison and analysis, we find that: a) GRU usually performs better than LSTM, for possibly GRU is able to modulate the previous memory content through the learned reset gates, helping to model the long-span dependence more efficiently for speech sequence; b) LSTMP shows comparable performance with GRU, since LSTMP has the similar ability of information selection and combination by an automatic learned linear transformation in a weight-sharing way. In experiments, a visual analysis method is adopted to understand the historical information selection mechanism in RNNs in contrast to DNN. Experimental results on three different speech recognition tasks demonstrate the above conclusions and 5%-13% relative PER or CER reduction is observed.
关键词Gated Recurrent Neural Networks Long Short-term Memory Unit Gated Recurrent Neural Networks Long Short-term Memory Projected Unit
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/19652
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Yuanyuan Zhao
作者单位Institute of Automation, Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Zhao, Yuanyuan,Li, Jie,Xu, Shuang,et al. Investigating Gated Recurrent Neural Networks for Acoustic Modeling[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
Investigating Gated (198KB)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
[Zhao, Yuanyuan]的文章
[Li, Jie]的文章
[Xu, Shuang]的文章
百度学术
百度学术中相似的文章
[Zhao, Yuanyuan]的文章
[Li, Jie]的文章
[Xu, Shuang]的文章
必应学术
必应学术中相似的文章
[Zhao, Yuanyuan]的文章
[Li, Jie]的文章
[Xu, Shuang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Investigating Gated Recurrent Neural Networks for Acoustic Modeling-camera.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。