发布求助
文献互助 智能选刊 最新文献

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)最新文献

筛选
英文 中文
Labelwalking nonnegative matrix factorization 标签行走非负矩阵分解
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178381
L. Lan, Naiyang Guan, Xiang Zhang, Xuhui Huang, Zhigang Luo
{"title":"Labelwalking nonnegative matrix factorization","authors":"L. Lan, Naiyang Guan, Xiang Zhang, Xuhui Huang, Zhigang Luo","doi":"10.1109/ICASSP.2015.7178381","DOIUrl":"https://doi.org/10.1109/ICASSP.2015.7178381","url":null,"abstract":"Semi-supervised learning (SSL) utilizes plenty of unlabeled examples to boost the performance of learning from limited labeled examples. Due to its great discriminant power, SSL has been widely applied to various real-world tasks such as information retrieval, pattern recognition, and speech separa- tion. Label propagation (LP) is a popular SSL method which propagates labels through the dataset along high density areas defined by unlabeled examples, LP assumes nearby examples should share the same label, thus, it unavoidably pushes the labels to the wrong examples, especially when different la- beled examples are not strictly separated. Seed K-means uses labeled examples to initialize class centers, and avoid getting stuck in poor local optima comparing to traditional K-means, however the hard constraint of each example's membership makes Seed K-means failed in many real world applications. This paper proposes a novel label walking nonnegative matrix factorization method (LWNMF) to handle labeled examples in SSL based on the framework of NMF. LWNMF decomposes the whole dataset into the product of a basis matrix and a coefficient matrix, and to travel labels to unlabeled examples, LWNMF regards the class indicators of labeled examples as their coefficients and iteratively updates both basis matrix and coefficients of unlabeled examples. Since LWNMF learns comprehensive class centroids, labels iteratively walk to unlabeled examples through these significant centroids.","PeriodicalId":117666,"journal":{"name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122460844","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
Logistic similarity metric learning for face verification 人脸验证的逻辑相似性度量学习
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178311
Lilei Zheng, Khalid Idrissi, Christophe Garcia, S. Duffner, A. Baskurt
{"title":"Logistic similarity metric learning for face verification","authors":"Lilei Zheng, Khalid Idrissi, Christophe Garcia, S. Duffner, A. Baskurt","doi":"10.1109/ICASSP.2015.7178311","DOIUrl":"https://doi.org/10.1109/ICASSP.2015.7178311","url":null,"abstract":"This paper presents a new method for similarity metric learning, called Logistic Similarity Metric Learning (LSML), where the cost is formulated as the logistic loss function, which gives a probability estimation of a pair of faces being similar. Especially, we propose to shift the similarity decision boundary gaining significant performance improvement. We test the proposed method on the face verification problem using four single face descriptors: LBP, OCLBP, SIFT and Gabor wavelets. Extensive experimental results on the LFW-a data set demonstrate that the proposed method achieves competitive state-of-the-art performance on the problem of face verification.","PeriodicalId":117666,"journal":{"name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"198 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122589245","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: 18
Sparse and cross-term free time-frequency distribution based on Hermite functions 基于Hermite函数的稀疏交叉项自由时频分布
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178661
B. Jokanović, M. Amin
{"title":"Sparse and cross-term free time-frequency distribution based on Hermite functions","authors":"B. Jokanović, M. Amin","doi":"10.1109/ICASSP.2015.7178661","DOIUrl":"https://doi.org/10.1109/ICASSP.2015.7178661","url":null,"abstract":"Hermite functions are an effective tool for improving the resolution of the single-window spectrogram. In this paper, we analyze the Hermite functions in the ambiguity domain and show that the higher order terms can introduce undesirable cross-terms in the multiwindow spectrogram. The optimal number of Hermite functions depends on the location and spread of signal auto-terms in the ambiguity domain. We apply and compare several sparsity measures, namely ℓ1 norm, the Gini index and the time-frequency concentration measure, for determining the optimal number of Hermite functions, leading to the most desirable time-frequency representation. Among the employed measures, the Gini index provides the sparsest solution. This solution corresponds to a well-concentrated and cross-term reduced time-frequency signature.","PeriodicalId":117666,"journal":{"name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122623325","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: 3
Model-based parameters estimation of non-stationary signals using time warping and a measure of spectral concentration 基于模型的非平稳信号参数估计使用时间翘曲和测量频谱浓度
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178663
A. Anghel, Gabriel Vasile, C. Ioana, R. Cacoveanu, S. Ciochină
{"title":"Model-based parameters estimation of non-stationary signals using time warping and a measure of spectral concentration","authors":"A. Anghel, Gabriel Vasile, C. Ioana, R. Cacoveanu, S. Ciochină","doi":"10.1109/ICASSP.2015.7178663","DOIUrl":"https://doi.org/10.1109/ICASSP.2015.7178663","url":null,"abstract":"This paper proposes a parameters estimation algorithm for signals composed of multiple non-stationary components having the same basis modulation function which is described by an a priori known model and depends on a few unknown parameters. The procedure is based on time warping the signal in turn with every basis function resulted from different model parameters combinations and evaluating the concentration of the warped signal spectrum. The estimated parameters of the model are the ones which provide the best spectral concentration. Onwards, the amplitude, phase and modulation rate for each component are determined from the signal warped with the optimal basis function. The algorithm is tested with simulations and real data consisting of de-chirped radar signals and acoustic signals with harmonic components from underwater mammals.","PeriodicalId":117666,"journal":{"name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123022140","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: 6
Sound event detection in real life recordings using coupled matrix factorization of spectral representations and class activity annotations 使用谱表示和类活动注释的耦合矩阵分解在真实生活记录中的声音事件检测
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7177950
A. Mesaros, T. Heittola, O. Dikmen, T. Virtanen
{"title":"Sound event detection in real life recordings using coupled matrix factorization of spectral representations and class activity annotations","authors":"A. Mesaros, T. Heittola, O. Dikmen, T. Virtanen","doi":"10.1109/ICASSP.2015.7177950","DOIUrl":"https://doi.org/10.1109/ICASSP.2015.7177950","url":null,"abstract":"Methods for detection of overlapping sound events in audio involve matrix factorization approaches, often assigning separated components to event classes. We present a method that bypasses the supervised construction of class models. The method learns the components as a non-negative dictionary in a coupled matrix factorization problem, where the spectral representation and the class activity annotation of the audio signal share the activation matrix. In testing, the dictionaries are used to estimate directly the class activations. For dealing with large amount of training data, two methods are proposed for reducing the size of the dictionary. The methods were tested on a database of real life recordings, and outperformed previous approaches by over 10%.","PeriodicalId":117666,"journal":{"name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114427460","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: 104
Dynamic ROI based on K-means for remote photoplethysmography 基于K-means的光电容积脉搏波动态ROI
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178182
Litong Feng, L. Po, Xuyuan Xu, Yuming Li, C. Cheung, K. Cheung, Fang Yuan
{"title":"Dynamic ROI based on K-means for remote photoplethysmography","authors":"Litong Feng, L. Po, Xuyuan Xu, Yuming Li, C. Cheung, K. Cheung, Fang Yuan","doi":"10.1109/ICASSP.2015.7178182","DOIUrl":"https://doi.org/10.1109/ICASSP.2015.7178182","url":null,"abstract":"Remote imaging photoplethysmography (RIPPG) can achieve contactless human vital signs monitoring. Though the remote operation mode brings a great convenience for RIPPG applications, the RIPPG signal quality is limited by the remote nature. Improving the RIPPG signal quality becomes an essential task in the clinical application of RIPPG. Since the region of interest (ROI) of the RIPPG transforms from a point to an area, there is a new approach to improving the RIPPG signal quality through refining the ROI. In this paper, we propose a dynamic ROI for RIPPG, which can automatically select the skin regions corresponding to good quality RIPPG signals. First, a fixed ROI is divided into non-overlapped blocks. Then two features are proposed to perform no-reference quality assessment for RIPPG signals from different blocks. After that, K-means clustering operates in a two dimensional feature space. A dynamic ROI can be selected for a video segment based on the clustering result, updated every two seconds. Nineteen healthy subjects were enrolled to test the proposed ROI selection method on both the facial region and the palmar region. Experimental results of heart rate measurement show that the proposed dynamic ROI method for RIPPG can effectively improve the RIPPG signal quality, compared with the state-of-the-art ROI methods for RIPPG.","PeriodicalId":117666,"journal":{"name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114609386","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: 24
Direction-of-arrival estimation of speech sources under aliasing conditions 混叠条件下语音源的到达方向估计
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7177920
V. Reddy, Andy W. H. Khong
{"title":"Direction-of-arrival estimation of speech sources under aliasing conditions","authors":"V. Reddy, Andy W. H. Khong","doi":"10.1109/ICASSP.2015.7177920","DOIUrl":"https://doi.org/10.1109/ICASSP.2015.7177920","url":null,"abstract":"Due to practical considerations the microphone spacing is increased to achieve improved resolution by violating the spatial Nyquist criterion. Accompanied aliasing components adversely affect the identifiability of the source direction peaks. We investigate the effect of aliasing on the spatial spectrum of the steered minimum variance distortionless response (STMV) method and propose a novel multi-stage scheme assisted by subband decomposition for suppressing aliasing components. The performance of the proposed technique, evaluated with simulations and recorded room responses, reflects the improvement in the identifiability of accurate source directions under aliasing conditions.","PeriodicalId":117666,"journal":{"name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122116085","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: 6
Nonlocal means image denoising based on bidirectional principal component analysis 基于双向主成分分析的非局部均值图像去噪
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178173
Hsin-Hui Chen, Jian-Jiun Ding
{"title":"Nonlocal means image denoising based on bidirectional principal component analysis","authors":"Hsin-Hui Chen, Jian-Jiun Ding","doi":"10.1109/ICASSP.2015.7178173","DOIUrl":"https://doi.org/10.1109/ICASSP.2015.7178173","url":null,"abstract":"In this paper, a very efficient image denoising scheme, which is called nonlocal means based on bidirectional principal component analysis, is proposed. Unlike conventional principal component analysis (PCA) based methods, which stretch a 2D matrix into a 1D vector and ignores the relations between different rows or columns, we adopt the technique of bidirectional PCA (BDPCA), which preserves the spatial structure and extract features by reducing the dimensionality in both column and row directions. Moreover, we also adopt the coarse-to-fine procedure without performing nonlocal means iteratively. Simulations demonstrated that, with the proposed scheme, the denoised image can well preserve the edges and texture of the original image and the peak signal-to-noise-ratio is higher than that of other methods in almost all the cases.","PeriodicalId":117666,"journal":{"name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116840795","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
An adaptive low-complexity detection method for statistical signal transmission under time-varying channels 时变信道下统计信号传输的自适应低复杂度检测方法
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178705
Tianheng Xu, Sha Yao, Honglin Hu
{"title":"An adaptive low-complexity detection method for statistical signal transmission under time-varying channels","authors":"Tianheng Xu, Sha Yao, Honglin Hu","doi":"10.1109/ICASSP.2015.7178705","DOIUrl":"https://doi.org/10.1109/ICASSP.2015.7178705","url":null,"abstract":"Based on orthogonal frequency division multiplexing (OFDM) systems, an additional individual data transmission can be established in statistical spectrum domain, which can be adopted for specific applications. However, the performance of existing detection methods for this kind of transmission will be severely restricted when the channel coefficients are dynamic within each observation window. In this paper, we propose an adaptive detection method for statistical signal transmission. This method has adequate adaptability for different channel varying rates, while maintaining low complexity. Simulation results show that the proposed method achieves significant performance gain compared to the original method under time varying channels.","PeriodicalId":117666,"journal":{"name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129572700","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: 2
Robust joint beamforming and artificial noise design for amplify-and-forward multi-antenna relay systems 放大前向多天线中继系统的鲁棒联合波束形成和人工噪声设计
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178267
Lijian Zhang, Liang Jin, W. Luo, Yanqun Tang, Dingjiu Yu
{"title":"Robust joint beamforming and artificial noise design for amplify-and-forward multi-antenna relay systems","authors":"Lijian Zhang, Liang Jin, W. Luo, Yanqun Tang, Dingjiu Yu","doi":"10.1109/ICASSP.2015.7178267","DOIUrl":"https://doi.org/10.1109/ICASSP.2015.7178267","url":null,"abstract":"In this paper, we address physical layer security for amplify-and-forward (AF) multi-antenna relay systems in the presence of multiple eavesdroppers. A robust joint design of cooperative beamforming (CB) and artificial noise (AN) is proposed with imperfect channel state information (CSI) of both the destination and the eavesdroppers. We aim to maximize the worst-case secrecy rate subject to the sum power and the per-antenna power constraints at the relay. Such joint design problem is non-convex. By utilizing the semidefinite relaxation (SDR) technique, S-procedure and the successive convex approximation (SCA) algorithm, the original non-convex optimization problem is recast into a series of semidefinite programs (SDPs) which can be efficiently solved using interior-methods. Simulation results are presented to verify the effectiveness of the proposed design.","PeriodicalId":117666,"journal":{"name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129616502","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: 3
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信