Multidimensional Residual Learning Based on Recurrent Neural Networks for Acoustic Modeling
Zhao, Yuanyuan; Xu, Shuang; Xu, Bo; Yuanyuan Zhao
2016-09
会议名称Interspeech2016
页码3419-3423
会议日期September 8-12
会议地点San Francisco, USA
摘要Theoretical and empirical evidences indicate that the depth of neural networks is crucial to acoustic modeling in speech recognition tasks. Unfortunately, the situation in practice always is that with the depth increasing, the accuracy gets saturated and then degrades rapidly.
    In this paper, a novel multidimensional residual learning architecture is proposed to address this degradation of deep recurrent neural networks (RNNs) on acoustic modeling by further exploring the spatial and temporal dimensions. In the spatial dimension, shortcut connections are introduced to RNNs, along which the information can flow across several layers without attenuation. In the temporal dimension, we cope with the degradation problem by regulating temporal granularity, namely, splitting the input sequence into several parallel sub-sequences, which can ensure information flowing across the time axis unimpededly. Finally, we place a row convolution layer on the top of all recurrent layers to comprehend appropriate information from several parallel sub-sequences to feed to the classifier. Experiments are illustrated on two quite different speech recognition tasks and 10% relative performance improvements are observed.
关键词Acoustic Modeling Multidimensional Residual Learning Long Short-term Memory Block Row Convolution Layer
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/173211/19648
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,Xu, Shuang,Xu, Bo,et al. Multidimensional Residual Learning Based on Recurrent Neural Networks for Acoustic Modeling[C],2016:3419-3423.
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
Multidimensional Res(298KB)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
[Xu, Shuang]的文章
[Xu, Bo]的文章
百度学术
百度学术中相似的文章
[Zhao, Yuanyuan]的文章
[Xu, Shuang]的文章
[Xu, Bo]的文章
必应学术
必应学术中相似的文章
[Zhao, Yuanyuan]的文章
[Xu, Shuang]的文章
[Xu, Bo]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Multidimensional Residual Learning Based on Recurrent Neural Networks for Acoustic Modeling.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。