Tunable time delay neural networks for isolated word recognition

Duanpei Wu, J. Gowdy
{"title":"Tunable time delay neural networks for isolated word recognition","authors":"Duanpei Wu, J. Gowdy","doi":"10.1109/SECON.1995.513088","DOIUrl":null,"url":null,"abstract":"Describes a new neural network structure and a corresponding new sequential training technique for speech recognition. The proposed system is a modification of the original time delay neural network (TDNN) structure of Waibel et al. [1989]. The new structure consists of a group of sub-nets, and each isolated word or phoneme to be recognized corresponds to one sub-net. Since each sub-net deals with only one recognition unit, it may be trained independently. Each sub-net is a TDNN which the authors train with a new sequential training algorithm. The system has attained close to 100% accuracy for a multi-speaker, isolated word recognition task and 86.44% accuracy for a three voiced-stop-consonants (\"B\", \"D\" and \"G\"), speaker-independent phoneme recognition task. Results for phoneme recognition compared favorably with the best result obtained by Bryant [1992] using Sawai's block windowed neural network architecture with improvement by 14.44% for the same task.","PeriodicalId":334874,"journal":{"name":"Proceedings IEEE Southeastcon '95. Visualize the Future","volume":"20 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1995-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings IEEE Southeastcon '95. Visualize the Future","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SECON.1995.513088","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Describes a new neural network structure and a corresponding new sequential training technique for speech recognition. The proposed system is a modification of the original time delay neural network (TDNN) structure of Waibel et al. [1989]. The new structure consists of a group of sub-nets, and each isolated word or phoneme to be recognized corresponds to one sub-net. Since each sub-net deals with only one recognition unit, it may be trained independently. Each sub-net is a TDNN which the authors train with a new sequential training algorithm. The system has attained close to 100% accuracy for a multi-speaker, isolated word recognition task and 86.44% accuracy for a three voiced-stop-consonants ("B", "D" and "G"), speaker-independent phoneme recognition task. Results for phoneme recognition compared favorably with the best result obtained by Bryant [1992] using Sawai's block windowed neural network architecture with improvement by 14.44% for the same task.
用于孤立词识别的可调时滞神经网络
描述了一种新的神经网络结构和相应的新的语音识别序列训练技术。所提出的系统是对Waibel等[1989]的原始时滞神经网络(TDNN)结构的改进。新结构由一组子网组成,每个待识别的孤立词或音素对应一个子网。由于每个子网只处理一个识别单元,因此可以独立地进行训练。每个子网络是一个TDNN,作者使用一种新的顺序训练算法对其进行训练。该系统在多说话人、孤立的单词识别任务中达到接近100%的准确率,在三个语音停顿辅音(“B”、“D”和“G”)、独立于说话人的音素识别任务中达到86.44%的准确率。音素识别的结果与Bryant[1992]使用Sawai的块窗口神经网络架构获得的最佳结果相比,改进了14.44%。
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 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信