Word-level Permutation and Improved Lower Frame Rate for RNN-Based Acoustic Modeling
Yuanyuan Zhao1,2; Shiyu Zhou1,2; Shuang Xu1; Bo Xu1
2017
会议名称iconip2017
会议录名称iconip2017
页码859-869
会议日期November 14-18, 2017
会议地点Guangzhou, China
摘要Recently, the RNN-based acoustic model has shown promising performance. However, its generalization ability to multiple scenarios is not powerful enough for two reasons. Firstly, it encodes inter-word dependency, which conflicts with the nature that an acoustic model should model the pronunciation of words only. Secondly, the RNN-based acoustic model depicting the inner-word acoustic trajectory frame-by-frame is too precise to tolerate small distortions. In this work, we propose two variants to address aforementioned two problems. One is the word-level permutation, i.e. the order of input features and corresponding labels is shuffled with a proper probability according to word boundaries. It aims to eliminate inter-word dependencies. The other one is the improved LFR (iLFR) model, which equidistantly splits the original sentence into N utterances to overcome the discarding data in LFR model. Results based on LSTM RNN demonstrate 7\% relative performance improvement by jointing the word-level permutation and iLFR.
关键词Rnn-based Acoustic Model Acoustic Trajectory Lower Frame Rate Word-level Permutation
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/173211/15429
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1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Yuanyuan Zhao,Shiyu Zhou,Shuang Xu,et al. Word-level Permutation and Improved Lower Frame Rate for RNN-Based Acoustic Modeling[C],2017:859-869.
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
Word-Level Permutati(513KB)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
[Yuanyuan Zhao]的文章
[Shiyu Zhou]的文章
[Shuang Xu]的文章
百度学术
百度学术中相似的文章
[Yuanyuan Zhao]的文章
[Shiyu Zhou]的文章
[Shuang Xu]的文章
必应学术
必应学术中相似的文章
[Yuanyuan Zhao]的文章
[Shiyu Zhou]的文章
[Shuang Xu]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Word-Level Permutation and Improved Lower Frame Rate for RNN-Based 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。