发布求助
文献互助 智能选刊 最新文献

21st European Signal Processing Conference (EUSIPCO 2013)最新文献

筛选
英文 中文
Graph-based bayesian approach for transient interference suppression 基于图的瞬态干扰抑制贝叶斯方法
21st European Signal Processing Conference (EUSIPCO 2013) Pub Date : 2013-09-09 DOI: 10.5281/ZENODO.43433
R. Talmon, I. Cohen, S. Gannot, R. Coifman
{"title":"Graph-based bayesian approach for transient interference suppression","authors":"R. Talmon, I. Cohen, S. Gannot, R. Coifman","doi":"10.5281/ZENODO.43433","DOIUrl":"https://doi.org/10.5281/ZENODO.43433","url":null,"abstract":"In this paper, we present a method for transient interference suppression. The main idea is to learn the intrinsic geometric structure of the transients instead of relying on estimates of noise statistics. The transient interference structure is captured via a parametrization of a graph constructed from the measurements. This parametrization is viewed as an empirical model for transients and is used for building a filter that extracts transients from noisy speech. We present a model-based supervised algorithm, in which the graph-based empirical model is constructed in advance from training recordings, and then extended to new incoming measurements. This paper extends previous studies and presents a new Bayesian approach for empirical model extension that takes into account both the structure of the transients as well as the dynamics of speech signals.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"39 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117246720","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
Speaker verification using Secure Binary Embeddings 使用安全二进制嵌入的说话人验证
21st European Signal Processing Conference (EUSIPCO 2013) Pub Date : 2013-09-09 DOI: 10.5281/ZENODO.43432
José Portêlo, B. Raj, P. Boufounos, I. Trancoso, A. Abad
{"title":"Speaker verification using Secure Binary Embeddings","authors":"José Portêlo, B. Raj, P. Boufounos, I. Trancoso, A. Abad","doi":"10.5281/ZENODO.43432","DOIUrl":"https://doi.org/10.5281/ZENODO.43432","url":null,"abstract":"This paper addresses privacy concerns in voice biometrics. Conventional remote speaker verification systems rely on the system to have access to the user's recordings, or features derived from them, and also a model of the user's voice. In the proposed approach, the system has access to none of them. The supervectors extracted from the user's recordings are transformed to bit strings in a way that allows the computation of approximate distances, instead of exact ones. The key to the transformation uses a hashing scheme known as Secure Binary Embeddings. An SVM classifier with a modified kernel operates on the hashes. This allows speaker verification to be performed without exposing speaker data. Experiments showed that the secure system yielded similar results as its non-private counterpart. The approach may be extended to other types of biometric authentication.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115344993","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
Multisource clustering of remote sensing images with Entropy-based Dempster-Shafer fusion 基于熵的Dempster-Shafer融合遥感图像多源聚类
21st European Signal Processing Conference (EUSIPCO 2013) Pub Date : 2013-09-09 DOI: 10.5281/ZENODO.43368
S. Ranoeliarivao, F. D. Morsier, D. Tuia, S. Rakotoniaina, M. Borgeaud, J. Thiran, S. Rakotondraompiana
{"title":"Multisource clustering of remote sensing images with Entropy-based Dempster-Shafer fusion","authors":"S. Ranoeliarivao, F. D. Morsier, D. Tuia, S. Rakotoniaina, M. Borgeaud, J. Thiran, S. Rakotondraompiana","doi":"10.5281/ZENODO.43368","DOIUrl":"https://doi.org/10.5281/ZENODO.43368","url":null,"abstract":"In this paper, we propose a strategy for fusing clustering maps obtained with different remote sensing sources. Dempster-Shafer (DS) Theory is a powerful fusion method that allows to combine classifications from different sources and handles ignorance, imprecision and conflict between them. To do so, it attributes evidences (weights) to different hypothesis representing single or unions of classes. We introduce a fully unsupervised evidence assignment strategy exploiting the entropy among cluster memberships. Ambiguous pixels get stronger evidences for union of classes to better represent the uncertainty among them. On two multisource experiments, the proposed Entropy-based Dempster-Shafer (EDS) performs best along the different fusion methods with VHR images, when the single class accuracies from each source are complementary and one of the sources shows low overall accuracy.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115457815","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
Tracking with asynchronous binary readings and layout information in RFID systems with sense-a-tags 具有感应标签的RFID系统中异步二进制读数和布局信息跟踪
21st European Signal Processing Conference (EUSIPCO 2013) Pub Date : 2013-09-09 DOI: 10.5281/ZENODO.43721
Li Geng, M. Bugallo, P. Djurić
{"title":"Tracking with asynchronous binary readings and layout information in RFID systems with sense-a-tags","authors":"Li Geng, M. Bugallo, P. Djurić","doi":"10.5281/ZENODO.43721","DOIUrl":"https://doi.org/10.5281/ZENODO.43721","url":null,"abstract":"This paper addresses the problem of real-time indoor tracking of tagged objects in Ultra High Frequency Radio Frequency IDentification (RFID) systems with layout information and asynchronous readings. The method is based on binary detections and the model for the probability of detection is a function of both distance and angle between a tag and a reader and accounts for the possibility of a tag being in a dead-zone. A newly developed RFID component, called sense-a-tag, is used to improve the tracking performance, especially in areas with intersections and at portals, where the estimation of the direction of movement is important. A multi-hypothesis particle filtering method is applied for the tracking and its performance is demonstrated by computer simulations.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"2017 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123631501","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
High-quality self-embedding for JPEG-compressed digital images 高质量的自嵌入jpeg压缩数字图像
21st European Signal Processing Conference (EUSIPCO 2013) Pub Date : 2013-09-09 DOI: 10.5281/ZENODO.43582
Pawel Korus, Jaroslaw Bialas, A. Dziech
{"title":"High-quality self-embedding for JPEG-compressed digital images","authors":"Pawel Korus, Jaroslaw Bialas, A. Dziech","doi":"10.5281/ZENODO.43582","DOIUrl":"https://doi.org/10.5281/ZENODO.43582","url":null,"abstract":"This paper deals with the design of a self-embedding scheme for JPEG-compressed images. Most of existing schemes are compatible only with loss-less images. Few of them are capable of handling lossy compression, but deliver very low restoration fidelity, and support only small amounts of tampered content. In this study, we extend a recently proposed self-embedding model, and perform theoretical analysis of the impact of watermark extraction and block classification errors on the achievable reconstruction performance. The theoretical results are verified experimentally with a new scheme dedicated to JPEG. Our scheme achieves the average reconstruction quality between 28 dB and 33 dB, for the maximum allowed tampering rates of 50% and 20%, respectively.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122062275","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
Primary emitter localization using smartly initialized Metropolis-Hastings algorithm 主发射器定位采用智能初始化Metropolis-Hastings算法
21st European Signal Processing Conference (EUSIPCO 2013) Pub Date : 2013-09-09 DOI: 10.5281/ZENODO.43736
Suzan Ureten, A. Yongaçoğlu, E. Petriu
{"title":"Primary emitter localization using smartly initialized Metropolis-Hastings algorithm","authors":"Suzan Ureten, A. Yongaçoğlu, E. Petriu","doi":"10.5281/ZENODO.43736","DOIUrl":"https://doi.org/10.5281/ZENODO.43736","url":null,"abstract":"The knowledge of the primary emitter location is important in cognitive radio networks as it is required to determine the exclusion region of the primary network. We show that interpolation based localization techniques do not provide accurate primary emitter localization; however they can provide significant complexity reduction when their estimates are used to initialize more accurate iterative localization techniques. In this paper, we generated interference maps using low complexity interpolation techniques and provided their coarse estimates to initialize a Metropolis-Hastings (MH)based localization algorithm. Our simulation results show that smart initialization of the MH algorithm eliminates tedious parameter tuning process and achieves significantly better localization performance than randomly initialized MH algorithm at a fraction of iterations.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114074487","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
Analysis of vowel deletion in continuous speech 连续语音中元音缺失现象分析
21st European Signal Processing Conference (EUSIPCO 2013) Pub Date : 2013-09-09 DOI: 10.5281/ZENODO.43725
R. G. Brunet, H. Murthy
{"title":"Analysis of vowel deletion in continuous speech","authors":"R. G. Brunet, H. Murthy","doi":"10.5281/ZENODO.43725","DOIUrl":"https://doi.org/10.5281/ZENODO.43725","url":null,"abstract":"Accurate transcription of the utterances during training is critical for recognition performance. The inherent properties of continuous/spontaneous speech across speakers, such as variation in pronunciation, poorly emphasized or over stressed words/sub-word units can lead to misalignment of the waveform at the sub-word unit level. The misalignment is caused by the deviation of the pronunciation from that defined by the pronunciation lexicon. This leads to insertion/deletion of subword units. This is primarily because the transcription is not specific to utterances. In this paper, an attempt is made to correct the transcription at the sub-word unit level using acoustic cues that are available in the waveform. Using sentence-level transcriptions, the transcription of a word is corrected in terms of the phonemes that make up the word. In particular, it is observed that vowels are either inserted or deleted. To support the proposed argument, mispronunciations in continuous speech are substantiated using signal processing and machine learning tools. An automatic data driven annotator exploiting the inferences drawn from the study is used to correct transcription errors. The results show that corrected pronunciations lead to higher likelihood for train utterances in the TIMIT corpus.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125111258","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
Estimation of pressure drop in pediatric endotracheal tubes during HFPV 估计小儿气管内管在HFPV期间的压降
21st European Signal Processing Conference (EUSIPCO 2013) Pub Date : 2013-09-09 DOI: 10.5281/ZENODO.43539
M. Ajčević, P. Accardo, E. Fornasa, U. Lucangelo
{"title":"Estimation of pressure drop in pediatric endotracheal tubes during HFPV","authors":"M. Ajčević, P. Accardo, E. Fornasa, U. Lucangelo","doi":"10.5281/ZENODO.43539","DOIUrl":"https://doi.org/10.5281/ZENODO.43539","url":null,"abstract":"High-frequency percussive ventilation (HFPV) is a ventilation modality which has been proved useful as an alternative to conventional mechanical ventilation. In clinical practice the ventilator measures the pressure that represents the sum of the pressure drop due to the endotracheal tube (ΔPEET) and the pressure dissipated to inflate lung. From the clinical point of view, it is of paramount importance to estimate the real amount of ΔPEET.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129259482","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
Constrained Kaczmarz's cyclic projections for unmixing hyperspectral data 解调高光谱数据的约束Kaczmarz循环投影
21st European Signal Processing Conference (EUSIPCO 2013) Pub Date : 2013-09-09 DOI: 10.5281/ZENODO.43534
P. Honeine, H. Lantéri, C. Richard
{"title":"Constrained Kaczmarz's cyclic projections for unmixing hyperspectral data","authors":"P. Honeine, H. Lantéri, C. Richard","doi":"10.5281/ZENODO.43534","DOIUrl":"https://doi.org/10.5281/ZENODO.43534","url":null,"abstract":"The estimation of fractional abundances under physical constraints is a fundamental problem in hyperspectral data processing. In this paper, we propose to adapt Kaczmarz's cyclic projections to solve this problem. The main contribution of this work is two-fold: On the one hand, we show that the non-negativity and the sum-to-one constraints can be easily imposed in Kaczmarz's cyclic projections, and on the second hand, we illustrate that these constraints are advantageous in the convergence behavior of the algorithm. To this end, we derive theoretical results on the convergence performance, both in the noiseless case and in the case of noisy data. Experimental results show the relevance of the proposed method.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129240165","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
Bayesian inversion of multi-mode NEMS mass spectrometry signal 多模NEMS质谱信号的贝叶斯反演
21st European Signal Processing Conference (EUSIPCO 2013) Pub Date : 2013-09-09 DOI: 10.5281/ZENODO.43398
R. Perenon, E. Sage, A. Mohammad-Djafari, L. Duraffourg, S. Hentz, A. Brenac, R. Morel, P. Grangeat
{"title":"Bayesian inversion of multi-mode NEMS mass spectrometry signal","authors":"R. Perenon, E. Sage, A. Mohammad-Djafari, L. Duraffourg, S. Hentz, A. Brenac, R. Morel, P. Grangeat","doi":"10.5281/ZENODO.43398","DOIUrl":"https://doi.org/10.5281/ZENODO.43398","url":null,"abstract":"Nano ElectroMechanical Systems are a new class of sensors that offers high sensitivity and opens new perspectives in the mass spectrometry field. This acquisition is performed in counting-mode, and the main tasks of associated information processing are to detect the molecules, to quantify their respective mass and to combine this information in order to recover the mass spectrum of the analysed solution. We propose a joint detection-quantification method based on a hierarchical description of the measurement system. Computation is done using a Reversible Jumps Monte-Carlo Markov-Chain algorithm. The approach we are describing in this communication solves the two problems of the joint impulse deconvolution on multiple output signals (multi-mode acquisition) and the non-linear relation between the observed signals and the mass of molecules, including the localization of the molecules on the sensor. We validate our method on both simulated and experimental data.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128233842","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
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