2011 IEEE 7th International Symposium on Intelligent Signal Processing最新文献_第4页

MMSE speech enhancement based on GMM and solving an over-determined system of equations 基于GMM和求解超定方程组的MMSE语音增强

2011 IEEE 7th International Symposium on Intelligent Signal Processing Pub Date : 2011-10-20 DOI: 10.1109/WISP.2011.6051692

S. Chehresa, M. Savoji

{"title":"MMSE speech enhancement based on GMM and solving an over-determined system of equations","authors":"S. Chehresa, M. Savoji","doi":"10.1109/WISP.2011.6051692","DOIUrl":"https://doi.org/10.1109/WISP.2011.6051692","url":null,"abstract":"A new and effective algorithm is proposed in this paper based on Gaussian Mixture Modelling (GMM) and Minimum Mean Square Error (MMSE) criterion for speech enhancement where no assumption is made on the nature or stationarity of the noise. No Voice Activity Detection (VAD) or any other means is used to estimate the input Signal to Noise Ratio (SNR). The mean vectors of the mixture models of spectral magnitudes derived from models of speech and different noise sources power spectra are used to form sets of over-determined system of equations, as many as noise source candidates, whose solutions lead to the MMSE estimations of speech and additive noise spectral magnitudes. The corresponding power spectra are then used for noise suppression by applying Wiener filtering carried out on overlapping frames. The input SNR is estimated and the nature of the noise involved is determined as by-products of the method used. Results are compared with codebook constrained methods that have shown very good results but suffer from long processing times. It is shown that, at the cost of a slight lower improvement in SNR and PESQ score, the new algorithm reduces the computation time to one fifth which makes it suitable for practical applications.","PeriodicalId":223520,"journal":{"name":"2011 IEEE 7th International Symposium on Intelligent Signal Processing","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133897481","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: 7

Wavelet-based image enhancement using fourth order PDE 基于小波的四阶PDE图像增强

2011 IEEE 7th International Symposium on Intelligent Signal Processing Pub Date : 2011-10-20 DOI: 10.1109/WISP.2011.6051688

Ehsan Nadernejad, Søren Forchhammer

引用次数: 7

Possibilities for intelligent sensor network assistance of product definition 智能传感器网络协助产品定义的可能性

2011 IEEE 7th International Symposium on Intelligent Signal Processing Pub Date : 2011-10-20 DOI: 10.1109/WISP.2011.6051722

L. Horváth, I. Rudas

{"title":"Possibilities for intelligent sensor network assistance of product definition","authors":"L. Horváth, I. Rudas","doi":"10.1109/WISP.2011.6051722","DOIUrl":"https://doi.org/10.1109/WISP.2011.6051722","url":null,"abstract":"Engineering for the development, application, and recycling of products is recently supported by fully integrated model of product. Prototyping is moving to virtual by the application of sophisticated product models for complex simulations. Simulations rely upon knowledge representing experience, expertise and intelligence of engineers in knowledge wares. Increasing proportion of this knowledge is placed in the product model in the form of active rules, checks, and reactions. In case of any change of these knowledge representations, relevant product model entities are modified accordingly. This knowledge must be verified by practice. Consequently, interaction of virtual and physical worlds is anticipated as a main area for future research in product model based virtual engineering systems. The authors developed and published a novel knowledge based method for the definition of product objects during the recent years. In this paper, they conceptualize a possible integration of intelligent sensor networks with active knowledge in product models. They propose introduction of physical information space in order to receive engineering object related information from preprocessed sensor data. The proposed novel method is based on intelligent capabilities both in sensor and product modeling.","PeriodicalId":223520,"journal":{"name":"2011 IEEE 7th International Symposium on Intelligent Signal Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114521479","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

A Multi-Channel Representation for images on quantum computers using the RGBα color space 基于RGBα色彩空间的量子计算机图像多通道表示

2011 IEEE 7th International Symposium on Intelligent Signal Processing Pub Date : 2011-10-20 DOI: 10.1109/WISP.2011.6051718

Bo Sun, P. Le, Abdullah M. Iliyasu, Fei Yan, J. A. Garcia, F. Dong, K. Hirota

引用次数: 137

Fuzzy modeling of natural terrain elevation from a 3D scanner point cloud 基于三维扫描仪点云的自然地形高程模糊建模

2011 IEEE 7th International Symposium on Intelligent Signal Processing Pub Date : 2011-10-20 DOI: 10.1109/WISP.2011.6051705

A. Mandow, Tomás J. Cantador, A. García-Cerezo, A. Reina, Jorge L. Martínez, J. Morales

引用次数: 9