2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)最新文献_第2页

Speech enhancement by iterating forward pass through U-net 通过U-net迭代前向传递的语音增强

2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) Pub Date : 2020-09-23 DOI: 10.23919/spa50552.2020.9241307

Tomasz Grzywalski, S. Drgas

引用次数: 1

Active tone elimination algorithm using FFT with interpolation and zero-padding 主动音调消除算法使用FFT与插值和零填充

2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) Pub Date : 2020-09-23 DOI: 10.23919/spa50552.2020.9241255

Michal Luczynski, A. Dobrucki, S. Brachmański

{"title":"Active tone elimination algorithm using FFT with interpolation and zero-padding","authors":"Michal Luczynski, A. Dobrucki, S. Brachmański","doi":"10.23919/spa50552.2020.9241255","DOIUrl":"https://doi.org/10.23919/spa50552.2020.9241255","url":null,"abstract":"This article presents a method for eliminating tonal components from acoustic signals. Tonal components are quasi-periodic signals whose amplitude, frequency and phase can change slowly with either a certain tendency or randomly. Active elimination of a single tonal component consists in adding a synthesized component with opposite polarity. The main challenge is to find a compromise between the frequency resolution and the delay resulting from the sample acquisition and the operation of the reset signal generation algorithm.The elimination is realized in three stages: detection of tonal components parameters, synthesis of the cancelling signal, addition of the cancelling signal to the input signal. Detection is carried out using the FFT transform, the resolution of which is increased by means of time windows, spectrum interpolation and zero-padding. Various methods of synthesis of the cancelling signal were also checked. An analysis of detection errors was performed compared to the standard FFT transform. An elimination simulation was also done to analyze the effectiveness of the reduction. The result of the work is the evaluation of the method for the application in the elimination of tonal components of acoustic signals as well as in systems of active reduction of narrowband noise.","PeriodicalId":157578,"journal":{"name":"2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127807721","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

CCTV based system for detection of anti-virus masks 基于CCTV的防病毒口罩检测系统

2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) Pub Date : 2020-09-23 DOI: 10.23919/spa50552.2020.9241303

K. Podbucki, J. Suder, T. Marciniak, A. Dabrowski

引用次数: 7

Algorithm for Human Fall Detection Based on Acceleration Measurement 基于加速度测量的人体跌倒检测算法

2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) Pub Date : 2020-09-23 DOI: 10.23919/spa50552.2020.9241243

Barbara Wilk, M. Augustyn, G. Wilk

引用次数: 0

Speaker verification with TIMIT corpus - some remarks on classical methods 用TIMIT语料库验证说话人——对经典方法的几点评述

2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) Pub Date : 2020-09-23 DOI: 10.23919/spa50552.2020.9241298

A. Dustor

引用次数: 0

The SMART4ALL toolbox for boosting technology and business development in South, Eastern and Central Europe 促进南欧、东欧和中欧技术和业务发展的SMART4ALL工具箱

2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) Pub Date : 2020-09-23 DOI: 10.23919/spa50552.2020.9241304

G. Keramidas

{"title":"The SMART4ALL toolbox for boosting technology and business development in South, Eastern and Central Europe","authors":"G. Keramidas","doi":"10.23919/spa50552.2020.9241304","DOIUrl":"https://doi.org/10.23919/spa50552.2020.9241304","url":null,"abstract":"SMART4ALL is a four-year Innovation Action project funded under Horizon 2020 framework under call DT-ICT-01-2019: Smart Anything Everywhere – Area 2: Customized low energy computing powering CPS and the IoT. The target of the project is to establish a unique Pan European network of Digital Innovation Hubs that will not only support innovation and reveal business opportunities across South, Eastern and Central Europe, but will build capacity via the development of self-sustained, cross-border pathfinder application experiments. The project will provide a total funding of 2,2 Mio Euros via 9 open calls and it will support 88 cross-border pathfinder application experiments from European consortia. Each experiment will get funding up to €80,000 and it will be supported with novel coaching services from world lead experts in ethics, technology, funding and business development. Apart from this, SMART4ALL sets forward a unique concept called Marketplace-as-a-Service (MaaS). Maas is a one-stop-smart-shop for startups, SMEs and slightly bigger companies. This presentation will introduce SMART4ALL and it will concentrate on the “Prepare for Growth” services offered by Maas.","PeriodicalId":157578,"journal":{"name":"2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127351073","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

Analytic Design of Uniform Circular Filter Banks 均匀圆形滤波器组的解析设计

2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) Pub Date : 2020-09-23 DOI: 10.23919/spa50552.2020.9241281

R. Matei

引用次数: 2

Artificial intelligence application to improve the performance of distance learning servers during the coronavirus pandemic threat period 应用人工智能提高新冠病毒大流行威胁期间远程学习服务器的性能

2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) Pub Date : 2020-09-23 DOI: 10.23919/spa50552.2020.9241301

P. Kłosowski

{"title":"Artificial intelligence application to improve the performance of distance learning servers during the coronavirus pandemic threat period","authors":"P. Kłosowski","doi":"10.23919/spa50552.2020.9241301","DOIUrl":"https://doi.org/10.23919/spa50552.2020.9241301","url":null,"abstract":"As of early 2020, almost all countries are fighting the coronavirus pandemic by implementing the rigorous restrictions recommended by the World Health Organisation to help reduce the number of infections as much as possible. The restrictions also apply to members of the academic community. The universities have suspended all teaching activities - except online. Most universities have introduced solutions for distance learning. However, organisation of distance education requires appropriate technological infrastructure. Providing the right IT infrastructure is not an easy challenge, because network devices and network servers note record-breaking peak loads during this time. It seems that there are potentially many possibilities of using artificial intelligence to improve the performance of distance learning platforms, information systems and network infrastructure in this difficult and demanding period. Examples of such use of artificial intelligence applications are presented in this article. The paper shows that the use of artificial intelligence to improve the operation of distance learning servers is potentially possible in many areas. It is also worth noting that the application of artificial neural networks and LSTM neural networks for this purpose seems very promising. The presentation of sample experiments and obtained results in this article seems to confirm this thesis.","PeriodicalId":157578,"journal":{"name":"2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115236063","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

Robust Beamforming Method Based on Double-layer Reconstruction of Covariance Matrix 基于协方差矩阵双层重构的鲁棒波束形成方法

2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) Pub Date : 2020-09-23 DOI: 10.23919/spa50552.2020.9241257

Cao Silei, Li Tianyu, Wang Yao

引用次数: 1

Determination of Low-Level Audio Descriptors of a Musical Instrument Sound Using Neural Network 用神经网络确定乐器声音的低级音频描述符

2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) Pub Date : 2020-09-23 DOI: 10.23919/spa50552.2020.9241264

Maciej Blaszke, Damian Koszewski

{"title":"Determination of Low-Level Audio Descriptors of a Musical Instrument Sound Using Neural Network","authors":"Maciej Blaszke, Damian Koszewski","doi":"10.23919/spa50552.2020.9241264","DOIUrl":"https://doi.org/10.23919/spa50552.2020.9241264","url":null,"abstract":"Audio files and the audio channel of video files can be described with temporal, spectral, cepstral, and perceptual audio descriptors. The so-called low-level descriptors are closely related to the signal characteristics. One can discern at least three levels of extraction granularity from the signal: at any point in the signal, in small arbitrary regions (i.e., frames) and longer pre-segmented regions. Even though there are tools (e.g., MIRToolbox, Python/libROSA) available for computing these descriptors, the resulting feature vector is always redundant as it contains many high-correlated descriptors and there are some limitations connected to the performance of these tools. That is why, in this study, a method for obtaining those descriptors using Artificial Neural Network (ANN) with a deep structure (i.e., DNN) is proposed. In such a scheme, the raw audio signal representing a given musical instrument is fed to the DNN input. Such a network can be used as a standalone module or as a pre-trained part of the bigger architecture. The results of deep network performance in the context of MPEG-7 descriptor derivation are shown along with the loss function convergence and behavior.","PeriodicalId":157578,"journal":{"name":"2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","volume":"34 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123461214","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