2016 IEEE International Conference on Digital Signal Processing (DSP)最新文献_第6页

Extended AMP algorithm for correlated distributed compressed sensing model 相关分布式压缩感知模型的扩展AMP算法

2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868649

Yang Lu, Wei Dai

引用次数: 2

A robust DBN-vector based speaker verification system under channel mismatch conditions 信道失配条件下基于dbn向量的鲁棒说话人验证系统

2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868523

Disong Wang, Yuexian Zou, J. Liu, Y. Huang

{"title":"A robust DBN-vector based speaker verification system under channel mismatch conditions","authors":"Disong Wang, Yuexian Zou, J. Liu, Y. Huang","doi":"10.1109/ICDSP.2016.7868523","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868523","url":null,"abstract":"Channel variability is one of the largest challenges for speaker verification (SV) techniques. Techniques in the feature, model and score domains have been applied to mitigate the channel impact. In this paper, we strive to study on robust deep feature learning with the deep belief network (DBN) by using traditional spectral features such as MFCC or PLP. In detail, during the training phase, a DBN is trained to map spectral features to the corresponding speaker identity, then deep features extracted at kth hidden layers are selected where k is determined by maximizing the ratio between within-class distance and between-class distance. In the enrollment phase, the well-trained DBN is used to extract deep features at kth hidden layers, then kth-DBN-vector is formed by averaging these features. In the test phase, kth-DBN-vector is extracted for test utterance and compared to the enrolled kth-DBN-vector to make a verification decision. To validate the effectiveness of the learned DBN-vectors for speaker verification, extensive experiments have been purposely conducted on Mandarin corpuses. It is encouraged to see that our proposed DBN-vector based SV system is superior to the state-of-the-art i-vector based SV system under channel mismatch conditions in terms of equal error rate (EER) and minimum detection cost function (minDCF).","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132857427","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: 4

Camera anomaly detection based on morphological analysis and deep learning 基于形态分析和深度学习的相机异常检测

2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868559

Lingping Dong, Yongliang Zhang, Conglin Wen, Hongtao Wu

引用次数: 15

Off-grid DOA estimation using temporal block sparse Bayesian inference 基于时间块稀疏贝叶斯推理的离网DOA估计

2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868546

Hongyu Cui, Huiping Duan, Hao Liu

引用次数: 3

Generalized design method for the difference co-array of the sum co-array 和共阵的差分共阵的广义设计方法

2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868584

Jianyan Liu, Yanmei Zhang, Weijiang Wang, Yilong Lu

引用次数: 2

Deep learning feature representation for electrocardiogram identification 用于心电图识别的深度学习特征表示

2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868505

Xiafei Lei, Yue Zhang, Zongqing Lu

引用次数: 13

Compressive sensing based multi-frequency synthesis 基于压缩感知的多频合成

2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868651

Feng Li, T. Cornwell, F. Hoog, Lei Xin, Yi Guo

引用次数: 1

Deep learning-based recognition of underwater target 基于深度学习的水下目标识别

2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868522

Xu Cao, Xiaomin Zhang, Yang Yu, Letian Niu

引用次数: 56

A fast-convergent pre-conditioned conjugate gradient detection for massive MIMO uplink 大规模MIMO上行链路的快速收敛预条件共轭梯度检测

2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868573

Ye Xue, Chuan Zhang, Shunqing Zhang, X. You

{"title":"A fast-convergent pre-conditioned conjugate gradient detection for massive MIMO uplink","authors":"Ye Xue, Chuan Zhang, Shunqing Zhang, X. You","doi":"10.1109/ICDSP.2016.7868573","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868573","url":null,"abstract":"The scaling up of antennae and terminals in massive multiple-input multiple-output (MIMO) systems helps increase spectral efficiency at the penalty of prohibitive computational complexity. In linear minimum mean square error (MMSE) detection, this complexity is mainly resulted from solving large-scale linear equations. Admittedly, iterative approaches such as conjugate gradient (CG) method have theoretically demonstrated their capability in balancing both performance and complexity for massive MIMO detection. Their convergence rate turns out to be really slow for common applications where the base station-to-user antenna ratio decreases. To this end, by introducing a pre-conditioner based on incomplete Cholesky (IC) factorization, this paper proposes a pre-conditioned conjugate gradient (PCG) method, which successfully speeds up the convergence even for small station-to-user antenna ratio scenarios. The analytical as well as numerical results have indicated that the proposed PCG method outperforms the conventional CG method due to the 50% reduced spectral condition number κ. Complexity analysis shows that the proposed PCG method achieves over 75% reduction compared to the conventional Cholesky factorization scheme when N = 40.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116995075","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: 20

Robust particle PHD filter with sparse representation for multi-target tracking 基于稀疏表示的鲁棒粒子PHD滤波多目标跟踪

2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868562

Zeyu Fu, P. Feng, S. M. Naqvi, J. Chambers

{"title":"Robust particle PHD filter with sparse representation for multi-target tracking","authors":"Zeyu Fu, P. Feng, S. M. Naqvi, J. Chambers","doi":"10.1109/ICDSP.2016.7868562","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868562","url":null,"abstract":"Recently, sparse representation has been widely used in computer vision and visual tracking applications, including face recognition and object tracking. In this paper, we propose a novel robust multi-target tracking method by applying sparse representation in a particle probability hypothesis density (PHD) filter framework. We employ the dictionary learning method and principle component analysis (PCA) to train a static appearance model offline with sufficient training data. This pre-trained dictionary contains both colour histogram and oriented gradient histogram (HOG) features based on foreground target appearances. The tracker combines the pre-trained dictionary and sparse coding to discriminate the tracked target from background clutter. The sparse coefficients solved by ℓ1-minimization are employed to generate the likelihood function values, which are further applied in the update step of the proposed particle PHD filter. The proposed particle PHD filter is validated on two video sequences from publicly available CAVIAR and PETS2009 datasets, and demonstrates improved tracking performance in comparison with the traditional particle PHD filter.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124359535","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: 5