发布求助
文献互助 智能选刊 最新文献

2019 27th European Signal Processing Conference (EUSIPCO)最新文献

筛选
英文 中文
Robust Compressive Spectral Image Recovery Algorithm Using Dictionary Learning and Transform Tensor SVD 基于字典学习和变换张量SVD的鲁棒压缩光谱图像恢复算法
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902654
Y. Fonseca, Tatiana Gelvez, H. Arguello
{"title":"Robust Compressive Spectral Image Recovery Algorithm Using Dictionary Learning and Transform Tensor SVD","authors":"Y. Fonseca, Tatiana Gelvez, H. Arguello","doi":"10.23919/EUSIPCO.2019.8902654","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902654","url":null,"abstract":"This paper proposes a low-rank tensor minimization algorithm to recover a spectral image (SI) from a set of compressed observations. The proposal takes advantage of the transform tensor singular value decomposition (tt-SVD) to promote a low-rank structure on the recovered SI. The methodology has three stages. First, a poor low-rank version of the SI is estimated using the tt-SVD framework with the discrete cosine transform (DCT). Then, an orthogonal transform is learned from the initial estimation using dictionary learning. Finally, an algorithm to find a low-rank approximation of the SI in both, the DCT and the learned transform is introduced. Quantitative evaluation over two databases and two compressive optical systems shows that the proposed method improves the reconstruction quality in up to 10dB as well as it is robust in the presence of noise.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130231707","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
Separation of independent/dependent sources using copulas 使用copula分离独立/依赖源
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902639
N. Mamouni, H. Fenniri, A. Ghazdali, A. Hakim, A. Keziou
{"title":"Separation of independent/dependent sources using copulas","authors":"N. Mamouni, H. Fenniri, A. Ghazdali, A. Hakim, A. Keziou","doi":"10.23919/EUSIPCO.2019.8902639","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902639","url":null,"abstract":"In this paper, we introduce a new convolutive blind source separation approach for independent/dependent source components. The proposed approach represents an efficient tool for separating linear convolutive mixing models, especially, when the source components are statistically dependent. Its efficiency is illustrated by some simulation results.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134006619","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
Adaptive Pre-whitening Based on Parametric NMF 基于参数NMF的自适应预白化
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902763
A. Jaramillo, J. Nielsen, M. G. Christensen
{"title":"Adaptive Pre-whitening Based on Parametric NMF","authors":"A. Jaramillo, J. Nielsen, M. G. Christensen","doi":"10.23919/EUSIPCO.2019.8902763","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902763","url":null,"abstract":"Several speech processing methods assume that a clean signal is observed in white Gaussian noise (WGN). An argument against those methods is that the WGN assumption is not valid in many real acoustic scenarios. To take into account the coloured nature of the noise, a pre-whitening filter which renders the background noise closer to white can be applied. This paper introduces an adaptive pre-whitener based on a supervised non-negative matrix factorization (NMF), in which a pre-trained dictionary includes parametrized spectral information about the noise and speech sources in the form of autoregressive (AR) coefficients. Results show that the noise can get closer to white, in comparison to pre-whiteners based on conventional noise power spectral density (PSD) estimates such as minimum statistics and MMSE. A better pitch estimation accuracy can be achieved as well. Speech enhancement based on the WGN assumption shows a similar performance to the conventional enhancement which makes use of the background noise PSD estimate, which reveals that the proposed pre-whitener can preserve the signal of interest.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131521959","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
Path Loss at 5 GHz and 31 GHz for Two Distinct Indoor Airport Settings 两种不同室内机场设置的5 GHz和31 GHz路径损耗
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902509
D. Matolak, Mohanad Mohsen, Jinming Chen
{"title":"Path Loss at 5 GHz and 31 GHz for Two Distinct Indoor Airport Settings","authors":"D. Matolak, Mohanad Mohsen, Jinming Chen","doi":"10.23919/EUSIPCO.2019.8902509","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902509","url":null,"abstract":"Vehicular and indoor communications continue to grow. This pertains to applications in aviation as well, which is also experiencing rapid growth. Since a pre-requisite to reliable communication link design is accurate knowledge of the wireless channel, research on channel models for these environments is an active area of study, and this is the topic of this paper. In this work, we report on measurement and model results for propagation path loss in two indoor airport environments, in two frequency bands. The first environment is a typical small terminal building, with characteristics similar to indoor offices, and the second is a more unusual aircraft maintenance hangar. The hangar is a crowded environment with multiple aircraft and metallic objects. Our results are for both the 30 GHz band (specifically 31 GHz), which is being investigated for future 5th generation cellular and other applications, and for the 5 GHz band, for a comparison. Our results show that the airport terminal building exhibits path loss characteristics very similar to those of an indoor office environment, at both frequencies, and this is largely as expected. In contrast, the maintenance hangar path loss is less than that of non-line of sight terminal building regions, somewhat unexpectedly. We attribute this to the highly reflective hangar environment, which serves to compensate for reduced diffraction and increased blockage losses at 31 GHz.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131842360","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
End-to-end Audio Classification with Small Datasets – Making It Work 利用小型数据集进行端到端音频分类--让它发挥作用
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902712
Maximilian Schmitt, Björn Schuller
{"title":"End-to-end Audio Classification with Small Datasets – Making It Work","authors":"Maximilian Schmitt, Björn Schuller","doi":"10.23919/EUSIPCO.2019.8902712","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902712","url":null,"abstract":"Deep end-to-end learning is a promising approach for many types of audio classification tasks. However, in fields such as health care and medical diagnosis, training data can be scarce, which makes training a neural network from the raw waveform to the target a challenge. In this work, we focus on a public dataset of human snore sounds, categorised into four classes, where one particular class has only a few training samples. We emphasise the pitfalls that need to be taken into account when working with such data and propose an end-to-end model providing a performance similar to that of other deep and non-deep approaches. Furthermore, we show that a model using only convolutional layers outperforms a model employing also recurrent layers.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131226737","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: 9
Deep Spatio-Temporal Modeling for Object-Level Gaze-Based Relevance Assessment 基于对象级注视的相关性评估的深度时空建模
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902990
K. Stavridis, A. Psaltis, A. Dimou, G. Papadopoulos, P. Daras
{"title":"Deep Spatio-Temporal Modeling for Object-Level Gaze-Based Relevance Assessment","authors":"K. Stavridis, A. Psaltis, A. Dimou, G. Papadopoulos, P. Daras","doi":"10.23919/EUSIPCO.2019.8902990","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902990","url":null,"abstract":"The current work investigates the problem of objectlevel relevance assessment prediction, taking into account the user’s captured gaze signal (behaviour) and following the Deep Learning (DL) paradigm. Human gaze, as a sub-conscious response, is influenced from several factors related to the human mental activity. Several studies have so far proposed methodologies based on the use of gaze statistical modeling and naive classifiers for assessing images or image patches as relevant or not to the user’s interests. Nevertheless, the outstanding majority of literature approaches only relied so far on the use of handcrafted features and relative simple classification schemes. On the contrary, the current work focuses on the use of DL schemes that will enable the modeling of complex patterns in the captured gaze signal and the subsequent derivation of corresponding discriminant features. Novel contributions of this study include: a) the introduction of a large-scale annotated gaze dataset, suitable for training DL models, b) a novel method for gaze modeling, capable of handling gaze sensor errors, and c) a DL based method, able to capture gaze patterns for assessing image objects as relevant or non-relevant, with respect to the user’s preferences. Extensive experiments demonstrate the efficiency of the proposed method, taking also into consideration key factors related to the human gaze behaviour.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130727577","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
A Speech Reconstruction Algorithm via Iteratively Reweighted ℓ2 Minimization for MFCC Codec 基于迭代重加权最小化的MFCC编解码器语音重构算法
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902504
Gang Min, Xiongwei Zhang, Xiangyang Liu, Changqing Zhang, Yanpu Chen
{"title":"A Speech Reconstruction Algorithm via Iteratively Reweighted ℓ2 Minimization for MFCC Codec","authors":"Gang Min, Xiongwei Zhang, Xiangyang Liu, Changqing Zhang, Yanpu Chen","doi":"10.23919/EUSIPCO.2019.8902504","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902504","url":null,"abstract":"This paper presents an effective method to address the inverse problem of Mel-frequency cepstral analysis, and describes how to reconstruct the speech waveforms from Mel-frequency cepstral coefficients (MFCCs) directly. To exploit the sparse characteristics of speech in the frequency domain, an iteratively reweighted $ell_{2}$ minimization method is proposed to cope with the under-determined nature of the reconstruction problem. The lost phase information during Mel-frequency cepstral analysis procedure is recovered by the inverse short-time Fourier transform magnitude algorithm. Experiments are conducted over the TIMIT database and evaluated by several different kinds of measures. Experimental results demonstrate that the proposed method recovers speech with high articulation and intelligibility. Specifically, it sounds very close to the original speech when using the high-resolution MFCCs, the average STOI, PESQ score reaches 93% and 4.0, respectively. This method could be easily used for MFCC codec at low bit rate.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130839133","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
Complexity Scalable HEVC-to-AV1 Transcoding Based on Coding Tree Depth Inheritance 基于编码树深度继承的复杂性可扩展hevc - av1转码
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902565
Alex Borges, B. Zatt, M. Porto, L. Agostini, G. Corrêa
{"title":"Complexity Scalable HEVC-to-AV1 Transcoding Based on Coding Tree Depth Inheritance","authors":"Alex Borges, B. Zatt, M. Porto, L. Agostini, G. Corrêa","doi":"10.23919/EUSIPCO.2019.8902565","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902565","url":null,"abstract":"With the advent of the recently launched AOMedia Video 1 (AV1) bitstream specification, there is currently a need for converting legacy content encoded with the state-of-the-art High Efficiency Video Coding (HEVC) standard to the new format. However, transcoding is a complex task composed of a decoding and an encoding process in sequence, which requires long processing time and high energy consumption. This paper proposes a complexity scalable HEVC-to-AV1 transcoding solution with three operation modes, which allow adjusting the tradeoff between encoding efficiency and computational cost. The solution is based on the high correlation between block size decisions in HEVC and AV1, allowing the AV1 encoder to inherit Coding Tree depth information from the HEVC bitstream to constrain the AV1 re-encoding process. Experimental results for the three operation modes show a transcoding time reduction between 35.4% and 69.5% at the cost of a compression efficiency loss that varies between 4.9% and 16.8%.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133713805","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
Reduced Complexity Maximum Likelihood Detector for DFT-s-SEFDM Systems DFT-s-SEFDM系统的低复杂度最大似然检测器
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902942
Tong Wu, R. Grammenos
{"title":"Reduced Complexity Maximum Likelihood Detector for DFT-s-SEFDM Systems","authors":"Tong Wu, R. Grammenos","doi":"10.23919/EUSIPCO.2019.8902942","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902942","url":null,"abstract":"In this paper, we report on the design of a Complexity-Reduced Maximum Likelihood (CRML) detector for DFT-spread Spectrally Efficient Frequency Division Multiplexing (DFT-s-SEFDM) systems. DFT-s-SEFDM systems are similar to DFT-spread Orthogonal Frequency Division Multiplexing (DFT-s-OFDM) systems, yet offer improved spectral efficiency. Simulation results demonstrate that the CRML detector can achieve the same bit error rate (BER) performance as the ML detector in DFT-s-SEFDM systems at reduced computational complexity. Specifically, compared to a conventional ML detector, it is shown that CRML can decrease the search region by up to 2M times where M denotes the constellation cardinality. Depending on parameter configuration, CRML can offer up to two orders of magnitude improvement in execution runtime performance. CRML is best-suited to applications with small system sizes, for example, in narrowband Internet of Things (NB-IoT) networks.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134493089","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
The Art of Teaching Computers: The SIMSSA Optical Music Recognition Workflow System 计算机教学的艺术:SIMSSA光学音乐识别工作流系统
2019 27th European Signal Processing Conference (EUSIPCO) Pub Date : 2019-09-01 DOI: 10.23919/EUSIPCO.2019.8902658
Ichiro Fujinaga, Gabriel Vigliensoni
{"title":"The Art of Teaching Computers: The SIMSSA Optical Music Recognition Workflow System","authors":"Ichiro Fujinaga, Gabriel Vigliensoni","doi":"10.23919/EUSIPCO.2019.8902658","DOIUrl":"https://doi.org/10.23919/EUSIPCO.2019.8902658","url":null,"abstract":"In many machine learning systems, it would be effective to create a pedagogical environment where both the machines and the humans can incrementally learn to solve problems through interaction and adaptation. We are designing an optical music recognition workflow system within the SIMSSA (Single Interface for Music Score Searching and Analysis) project, where human operators/teachers can intervene to correct and teach the system at certain stages in the optical music recognition process so that both parties can learn from the errors and, consequently, the overall performance is increased progressively as more music scores are processed. In this environment, the humans are learning how to teach the machine more effectively.","PeriodicalId":319233,"journal":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133766931","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
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：604180095
Book学术官方微信
小红书