Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop最新文献_第6页

Segment-based speaker adaptation by neural network 基于分段的说话人神经网络自适应

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239497

K. Fukuzawa, H. Sawai, M. Sugiyama

引用次数: 4

Vector quantization of images using neural networks and simulated annealing 使用神经网络和模拟退火的图像矢量量化

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239486

M. Lech, Y. Hua

{"title":"Vector quantization of images using neural networks and simulated annealing","authors":"M. Lech, Y. Hua","doi":"10.1109/NNSP.1991.239486","DOIUrl":"https://doi.org/10.1109/NNSP.1991.239486","url":null,"abstract":"Vector quantization (VQ) has already been established as a very powerful data compression technique. Specification of the 'codebook', which contains the best possible collection of 'codewords', effectively representing the variety of source vectors to be encoded is one of the most critical requirements of VQ systems, and belongs, for most applications, to the class of hard optimization problems. A number of new approaches to codebook generation methods using neural networks (NN) and simulated annealing (SA) are presented and compared. The authors discuss the competitive learning algorithm (CL) and Kohonen's self-organizing feature maps (KSFM). The algorithms are examined using a new training rule and comparisons with the standard rule is included. A new solution to the problem of determining the 'closest' neural unit is also proposed. The second group of methods considered are all based on simulated annealing (SA). A number of improvements to and alternative constructions of the classical 'single path' simulated annealing algorithm are presented to address the problem of suboptimality of VQ codebook generation and provide methods by which solutions closer to the optimum are obtainable for similar computational effort.<<ETX>>","PeriodicalId":354832,"journal":{"name":"Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop","volume":"186 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":"131503399","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: 8

A relaxation neural network model for optimal multi-level image representation by local-parallel computations 基于局部并行计算的多级图像表示松弛神经网络模型

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239494

N. Sonehara

引用次数: 0

Edge detection for optical image metrology using unsupervised neural network learning 基于无监督神经网络学习的光学图像测量边缘检测

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239523

H. Aghajan, C. Schaper, T. Kailath

引用次数: 1

Improving learning rate of neural tree networks using thermal perceptrons 利用热感知器提高神经树网络的学习率

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239532

Ananth Sankar, R. Mammone

引用次数: 2

A hybrid continuous speech recognition system using segmental neural nets with hidden Markov models 基于隐马尔可夫模型的分段神经网络混合连续语音识别系统

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239507

G. Zavaliagkos, S. Austin, J. Makhoul, R. Schwartz

引用次数: 21

Learned representation normalization: attention focusing with multiple input modules 学习表征规范化:关注多个输入模块

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239530

M. L. Rossen

引用次数: 0

Restricted learning algorithm and its application to neural network training 限制性学习算法及其在神经网络训练中的应用

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239528

T. Miyamura, I. Yamada, K. Sakaniwa

引用次数: 0

A space-perturbance/time-delay neural network for speech recognition 用于语音识别的空间摄动/时滞神经网络

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239503

J. Ming, Chen Huihuang, S. Zhenkang

引用次数: 2

Speech recognition by combining pairwise discriminant time-delay neural networks and predictive LR-parser 结合两两判别时滞神经网络和预测lr解析器的语音识别

Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop Pub Date : 1991-09-30 DOI: 10.1109/NNSP.1991.239509

J. Takami, A. Kai, S. Sagayama

引用次数: 2