Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop最新文献

Connectionist speaker normalization and its applications to speech recognition 连接主义说话人归一化及其在语音识别中的应用

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239506

X.D. Huang, K. Lee, A. Waibel

引用次数: 12

Concept formation and statistical learning in nonhomogeneous neural nets 非齐次神经网络的概念形成与统计学习

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239538

R. Tutwiler, L. Sibul

引用次数: 0

An alternative proof of convergence for Kung-Diamantaras APEX algorithm Kung-Diamantaras APEX算法收敛性的另一个证明

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239537

H. Chen, R. Liu

引用次数: 6

Fuzzy tracking of multiple objects 多目标模糊跟踪

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1117/12.138232

L. Perlovsky

引用次数: 2

Workstation-based phonetic typewriter 基于工作站的语音打字机

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239514

T. Kohonen

引用次数: 9

On adaptive acquisition of spoken language 论口语的适应性习得

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239499

A. Gorin, S. Levinson, L. G. Miller, A. Gertner

{"title":"On adaptive acquisition of spoken language","authors":"A. Gorin, S. Levinson, L. G. Miller, A. Gertner","doi":"10.1109/NNSP.1991.239499","DOIUrl":"https://doi.org/10.1109/NNSP.1991.239499","url":null,"abstract":"At present, automatic speech recognition technology is based upon constructing models of the various levels of linguistic structure assumed to compose spoken language. These models are either constructed manually or automatically trained by example. A major impediment is the cost, or even the feasibility, of producing models of sufficient fidelity to enable the desired level of performance. The proposed alternative is to build a device capable of acquiring the necessary linguistic skills during the course of performing its task. The authors provide a progress report on their work in this direction, describing some principles and mechanisms upon which such a device might be based, and recounting several rudimentary experiments evaluating their utility. The basic principles and mechanisms underlying this research program are briefly reviewed. The authors have been investigating the application of those ideas to devices with spoken input, and which are capable of larger and more complex sets of actions. The authors propose some corollaries to those basic principles, thereby motivating extensions of earlier experimental mechanisms to these more complex devices. They also briefly describe these experimental systems and observe how they demonstrate the utility of their ideas.<<ETX>>","PeriodicalId":354832,"journal":{"name":"Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124112635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Adaline with adaptive recursive memory Adaline具有自适应递归内存

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239531

B. de Vries, J. Príncipe, P. Guedes de Oliveira

引用次数: 19

Word recognition with the feature finding neural network (FFNN) 基于特征寻找神经网络的词识别

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239513

T. Gramß

引用次数: 18

Note on generalization, regularization and architecture selection in nonlinear learning systems 非线性学习系统的泛化、正则化和结构选择

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239541

J. Moody

引用次数: 157

New discriminative training algorithms based on the generalized probabilistic descent method 基于广义概率下降法的判别训练新算法

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239512

Shigeru Katagiri, C.-H. Lee, B. Juang

引用次数: 167