A multi-target approach for isolated word recognition using artificial neural network |
| |
作者姓名: | QI Yingyong and BI Ning |
| |
作者单位: | Dept. of Speech and Hearing Sciences. University of Arizona. Tucson,AZ 85721 |
| |
摘 要: | I.TntroductionStatisticalandneuralnetworkmcthodsforpatternclassiflcationusesignificantlydifTerentapproachesintrainingaclassificr.Inthestatistica1approach,thcformationofaclassifier1arge1ydependsonthestatisticsofthetrainingpatternsand,insomecases,theassumptionsaboutthedistributionofthepopulation.Theneuralnetworkmethodisnon-parametricandcanbeadaptivcinthetrainingprocessl'l.Becauseofitssimplicityandflexibility,theneuralnetworkhasbecnincreasing1yusedforpatternclassiflcation.Itisnowwe11knownthatan…
|
A multi-target approach for isolated word recognition using artificial neural network |
| |
Authors: | QI Yingyong and BI Ning |
| |
Abstract: | We present a multi-target approach in network training for isolated word recognition. In this approach, each word was designated to produce output at more than one-target in the output laycr of the network during training.The specification of the target vector was mode based on the statistical or cluster structure of training patterns. Experiments consisted of classification of simulated data and isolated spoken words indicated that the multi-target approach improved the overall performance of the network. |
| |
Keywords: | Neural network Speech recognition |
本文献已被 CNKI 等数据库收录! |