2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)最新文献_第6页

Multi-view indoor scene reconstruction from compressed through-wall radar measurements using a joint bayesian sparse representation 基于联合贝叶斯稀疏表示的压缩穿墙雷达多视点室内场景重建

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178405

Van Ha Tang, A. Bouzerdoum, S. L. Phung, F. Tivive

{"title":"Multi-view indoor scene reconstruction from compressed through-wall radar measurements using a joint bayesian sparse representation","authors":"Van Ha Tang, A. Bouzerdoum, S. L. Phung, F. Tivive","doi":"10.1109/ICASSP.2015.7178405","DOIUrl":"https://doi.org/10.1109/ICASSP.2015.7178405","url":null,"abstract":"This paper addresses the problem of scene reconstruction, incorporating wall-clutter mitigation, for compressed multi-view through-the-wall radar imaging. We consider the problem where the scene is sensed using different reduced sets of frequencies at different antennas. A joint Bayesian sparse recovery framework is first employed to estimate the antenna signal coefficients simultaneously, by exploiting the sparsity and correlations between antenna signals. Following joint signal coefficient estimation, a subspace projection technique is applied to segregate the target coefficients from the wall contributions. Furthermore, a multitask linear model is developed to relate the target coefficients to the scene, and a composite scene image is reconstructed by a joint Bayesian sparse framework, taking into account the inter-view dependencies. Experimental results show that the proposed approach improves reconstruction accuracy and produces a composite scene image in which the targets are enhanced and the background clutter is attenuated.","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":"129945246","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

Supervised sparse coding with local geometrical constraints 局部几何约束下的监督稀疏编码

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178362

Hanchao Zhang, Jinhua Xu

引用次数: 1

Learning feature mapping using deep neural network bottleneck features for distant large vocabulary speech recognition 基于深度神经网络瓶颈特征的远距离大词汇语音识别学习特征映射

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178830

Ivan Himawan, P. Motlícek, David Imseng, B. Potard, Namhoon Kim, Jaewon Lee

引用次数: 30

Base Station clustering in heterogeneous network with finite backhaul capacity 回程容量有限的异构网络中的基站集群

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178501

Qian Zhang, Chen He, Ling-ge Jiang

{"title":"Base Station clustering in heterogeneous network with finite backhaul capacity","authors":"Qian Zhang, Chen He, Ling-ge Jiang","doi":"10.1109/ICASSP.2015.7178501","DOIUrl":"https://doi.org/10.1109/ICASSP.2015.7178501","url":null,"abstract":"This paper considers the Base Station (BS) clustering in a downlink heterogeneous network with finite backhaul capacity. We consider a tree structure network where each BS has only one incoming link and several outgoing links. The objective is to maximize the minimum rate among all users while satisfying the backhaul capacity constraint and the per-BS power constraint. We propose an algorithm that combines the bisection and the Alternating Direction Method of Multipliers (ADMM). The bisection search is conducted for the minimum rate. When it is given, we use ADMM to check the feasibility of the network while obeying the backhaul and power constraints. There are two steps involved in ADMM: i) a second order conic programming is used to calculate the beamformer; ii) a closed-form rule is used to determine the BS clustering. Due to the non-convexity and the non-smoothness, ADMM is not guaranteed to solve the problem. Therefore, we propose a revise step to further improve the performance. The simulation results show that the proposed algorithm outperforms the heuristic method and the revise step does improve the performance in all considered scenarios.","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":"128641933","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 beamformer and artificial noises for MISO wiretap channels with multiple eavesdroppers 多窃听器MISO窃听信道的鲁棒波束形成和人工噪声

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178544

S. Ohno, Y. Wakasa

引用次数: 0

Cepstral noise subtraction for robust automatic speech recognition 鲁棒自动语音识别的倒谱噪声减法

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7177994

R. Rehr, Timo Gerkmann

{"title":"Cepstral noise subtraction for robust automatic speech recognition","authors":"R. Rehr, Timo Gerkmann","doi":"10.1109/ICASSP.2015.7177994","DOIUrl":"https://doi.org/10.1109/ICASSP.2015.7177994","url":null,"abstract":"The robustness of speech recognizers towards noise can be increased by normalizing the statistical moments of the Mel-frequency cepstral coefficients (MFCCs), e. g. by using cepstral mean normalization (CMN) or cepstral mean and variance normalization (CMVN). The necessary statistics are estimated over a long time window and often, a complete utterance is chosen. Consequently, changes in the background noise can only be tracked to a limited extent which poses a restriction to the performance gain that can be achieved by these techniques. In contrast, algorithms recently developed for single-channel speech enhancement allow to track the background noise quickly. In this paper, we aim at combining speech enhancement techniques and feature normalization methods. For this, we propose to transform an estimate of the noise power spectral density to the MFCC domain, where we subtract it from the noisy MFCCs. This is followed by a conventional CMVN. For background noises that are too instationary for CMVN but can be tracked by the noise estimator, we show that this processing leads to an improvement in comparison to the sole application of CMVN. The observed performance gain emerges especially in low signal-to-noise-ratios.","PeriodicalId":117666,"journal":{"name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"30 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":"128972094","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

Automatic gain control and multi-style training for robust small-footprint keyword spotting with deep neural networks 基于深度神经网络的鲁棒小足迹关键词识别的自动增益控制和多风格训练

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178863

Rohit Prabhavalkar, R. Álvarez, Carolina Parada, Preetum Nakkiran, Tara N. Sainath

引用次数: 73

Stability analysis of the FBANC system having delay error in the estimated secondary path model 估计副路径模型中具有延迟误差的FBANC系统稳定性分析

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178053

Seong-Pil Moon, K. Son, T. Chang

引用次数: 1

Interference statistics in a random mmWave ad hoc network 随机毫米波自组织网络中的干扰统计

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178502

Andrew Thornburg, T. Bai, R. Heath

引用次数: 21

Dynamic zero-point attracting projection for time-varying sparse signal recovery 时变稀疏信号恢复的动态零点吸引投影

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7179020

Jiawei Zhou, Laming Chen, Yuantao Gu

引用次数: 3