Feature engineering in Context-Dependent Deep Neural Networks for conversational speech transcription

F. Seide, Gang Li, Xie Chen, Dong Yu
{"title":"Feature engineering in Context-Dependent Deep Neural Networks for conversational speech transcription","authors":"F. Seide, Gang Li, Xie Chen, Dong Yu","doi":"10.1109/ASRU.2011.6163899","DOIUrl":null,"url":null,"abstract":"We investigate the potential of Context-Dependent Deep-Neural-Network HMMs, or CD-DNN-HMMs, from a feature-engineering perspective. Recently, we had shown that for speaker-independent transcription of phone calls (NIST RT03S Fisher data), CD-DNN-HMMs reduced the word error rate by as much as one third—from 27.4%, obtained by discriminatively trained Gaussian-mixture HMMs with HLDA features, to 18.5%—using 300+ hours of training data (Switchboard), 9000+ tied triphone states, and up to 9 hidden network layers.","PeriodicalId":338241,"journal":{"name":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","volume":"48 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"690","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ASRU.2011.6163899","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 690

Abstract

We investigate the potential of Context-Dependent Deep-Neural-Network HMMs, or CD-DNN-HMMs, from a feature-engineering perspective. Recently, we had shown that for speaker-independent transcription of phone calls (NIST RT03S Fisher data), CD-DNN-HMMs reduced the word error rate by as much as one third—from 27.4%, obtained by discriminatively trained Gaussian-mixture HMMs with HLDA features, to 18.5%—using 300+ hours of training data (Switchboard), 9000+ tied triphone states, and up to 9 hidden network layers.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
会话语音转录中上下文相关深度神经网络的特征工程
我们从特征工程的角度研究了上下文相关的深度神经网络hmm或cd - dnn - hmm的潜力。最近,我们已经表明,对于独立于说话人的电话转录(NIST RT03S Fisher数据),cd - dnn - hmm使用300多个小时的训练数据(交换机),9000多个绑定三音状态和多达9个隐藏网络层,将单词错误率从带有HLDA特征的判别训练高斯混合hmm获得的27.4%降低到18.5%,减少了多达三分之一。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Applying feature bagging for more accurate and robust automated speaking assessment Towards choosing better primes for spoken dialog systems Accent level adjustment in bilingual Thai-English text-to-speech synthesis Fast speaker diarization using a high-level scripting language Evaluating prosodic features for automated scoring of non-native read speech
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1