Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing最新文献_第4页

Removal of residual crosstalk components in blind source separation using LMS filters 利用LMS滤波器去除盲源分离中残留串扰分量

Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing Pub Date : 2002-11-07 DOI: 10.1109/NNSP.2002.1030055

R. Mukai, S. Araki, H. Sawada, S. Makino

引用次数: 25

Linear input network for neural network automata model adaptation 线性输入网络对神经网络自动机模型的自适应

Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing Pub Date : 2002-11-07 DOI: 10.1109/NNSP.2002.1030073

F. Mana, R. Gemello

{"title":"Linear input network for neural network automata model adaptation","authors":"F. Mana, R. Gemello","doi":"10.1109/NNSP.2002.1030073","DOIUrl":"https://doi.org/10.1109/NNSP.2002.1030073","url":null,"abstract":"The paper describes an experimental investigation of the applicability of linear input networks (LIN) as a channel and noise adaptation technique for an application of the Loquendo neural network based speech recognizer in a car environment. The considered application is an automated call center that provides traffic information through a voice dialogue system. The connection to the call center is achieved by means of a commercial device placed in the car and made up of a microphone which is placed in front of the driver and equipped with an echo canceller and built-in noise reduction. The connection with the call center is set up through a GSM link. By experiment, the LIN technique adapts the basic neural network speech recognizer to this new environment. Some variants devoted to reducing the number of estimated parameters are also introduced. The LIN technique, is also compared with some classical denoising techniques based on noise spectral subtraction. The obtained results confirm the validity of LIN for channel and noise adaptation, while the introduced variants are a valid alternative when a reduced model size is important. The best performances in our specific application were of 57.14% error reduction versus the performance obtained by general acoustic models and were achieved by joint use of a LIN and noise spectral subtraction.","PeriodicalId":117945,"journal":{"name":"Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121592456","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: 0

Decision templates for the classification of bioacoustic time series 生物声学时间序列分类决策模板

Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing Pub Date : 2002-11-07 DOI: 10.1109/NNSP.2002.1030027

C. Dietrich, G. Palm, F. Schwenker

引用次数: 53

Accurate estimation of the signal baseline in DNA chromatograms DNA色谱中信号基线的准确估计

Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing Pub Date : 2002-11-07 DOI: 10.1109/NNSP.2002.1030015

L. Andrade, E. Manolakos

引用次数: 5

Minimax strategies for training classifiers under unknown priors 未知先验条件下分类器训练的极大极小策略

Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing Pub Date : 2002-11-07 DOI: 10.1109/NNSP.2002.1030036

R. Alaíz-Rodríguez, Jesús Cid-Sueiro

引用次数: 0

Biometric watermark authentication with multiple verification rule 多验证规则的生物特征水印认证

Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing Pub Date : 2002-11-07 DOI: 10.1109/NNSP.2002.1030071

T. Satonaka

引用次数: 27

Local minima effects on the transient performance of non-linear blind equalizers 局部极小值对非线性盲均衡器瞬态性能的影响

Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing Pub Date : 2002-11-07 DOI: 10.1109/NNSP.2002.1030088

J. Destro-Filho

引用次数: 0

Dynamic Bayesian network based speech recognition with pitch and energy as auxiliary variables 以音高和能量为辅助变量的动态贝叶斯网络语音识别

Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing Pub Date : 2002-11-07 DOI: 10.1109/NNSP.2002.1030075

T. A. Stephenson, J. Escofet, M. Magimai.-Doss, H. Bourlard

引用次数: 22

A stochastic method for minimizing functions with many minima 具有多个极小值的函数最小化的随机方法

Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing Pub Date : 2002-11-07 DOI: 10.1109/NNSP.2002.1030040

H. Ye, Zhiping Lin

引用次数: 5

Language model adaptation in speech recognition using document maps 基于文档地图的语音识别中的语言模型适应

Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing Pub Date : 2002-11-07 DOI: 10.1109/NNSP.2002.1030074

K. Lagus, M. Kurimo

引用次数: 6