{"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.