2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC)最新文献

筛选
英文 中文
Towards online source counting in speech mixtures applying a variational EM for complex Watson mixture models 用变分EM对复杂沃森混合模型进行语音混合的在线源计数
2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC) Pub Date : 2014-09-01 DOI: 10.1109/IWAENC.2014.6954009
Lukas Drude, Aleksej Chinaev, Dang Hai Tran Vu, Reinhold Häb-Umbach
{"title":"Towards online source counting in speech mixtures applying a variational EM for complex Watson mixture models","authors":"Lukas Drude, Aleksej Chinaev, Dang Hai Tran Vu, Reinhold Häb-Umbach","doi":"10.1109/IWAENC.2014.6954009","DOIUrl":"https://doi.org/10.1109/IWAENC.2014.6954009","url":null,"abstract":"This contribution describes a step-wise source counting algorithm to determine the number of speakers in an offline sce-nario. Each speaker is identified by a variational expectation maximization (VEM) algorithm for complex Watson mixture models and therefore directly yields beamforming vectors for a subsequent speech separation process. An observation selection criterion is proposed which improves the robustness of the source counting in noise. The algorithm is compared to an alternative VEM approach with Gaussian mixture models based on directions of arrival and shown to deliver improved source counting accuracy. The article concludes by extending the offline algorithm towards a low-latency online estimation of the number of active sources from the streaming input data.","PeriodicalId":218921,"journal":{"name":"2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128257408","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
Spatial perception of virtual X-Y recordings 虚拟X-Y记录的空间感知
2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC) Pub Date : 2014-09-01 DOI: 10.1109/IWAENC.2014.6953352
K. Kowalczyk, A. Craciun, Christian Dachmann, Emanuël Habets
{"title":"Spatial perception of virtual X-Y recordings","authors":"K. Kowalczyk, A. Craciun, Christian Dachmann, Emanuël Habets","doi":"10.1109/IWAENC.2014.6953352","DOIUrl":"https://doi.org/10.1109/IWAENC.2014.6953352","url":null,"abstract":"Spatial sound acquisition aims at capturing the sound field such that spatial cues present in the sound scene at the recording side are preserved at the reproduction side. The virtual microphone technique is a spatial recording method that allows for an arbitrary selection of the recording position and orientation. It exploits the parametric information about the sound field estimated using distributed microphone arrays in order to synthesize the virtual microphone signals that sound perceptually similar to the signals that would be recorded using physical microphones located at the same positions. In this paper, the quality of the spatial image in virtual stereo recordings is evaluated through a set of subjective experiments, including dedicated tests for distance and angle perception. The listening test results show that the spatial image captured using virtual microphones is perceptually close to the image recorded with physical microphones positioned analogously.","PeriodicalId":218921,"journal":{"name":"2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126304529","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
On near-field beamforming with smartphone-based ad-hoc microphone arrays 基于智能手机的特设麦克风阵列的近场波束形成
2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC) Pub Date : 2014-09-01 DOI: 10.1109/IWAENC.2014.6953345
N. Gaubitch, Jorge Martínez, W. Kleijn, R. Heusdens
{"title":"On near-field beamforming with smartphone-based ad-hoc microphone arrays","authors":"N. Gaubitch, Jorge Martínez, W. Kleijn, R. Heusdens","doi":"10.1109/IWAENC.2014.6953345","DOIUrl":"https://doi.org/10.1109/IWAENC.2014.6953345","url":null,"abstract":"Spatial audio processing using ad-hoc microphone arrays that consist of mobile devices, such as smartphones, is an attractive approach for future speech and audio capturing applications. However, many issues including microphone localization, clock synchronization and gain equalization, need consideration before such ad-hoc arrays can be applied in practice. An additional issue that needs to be considered is the microphone directivity of the devices. In this paper, we present measured microphone responses for nine different smartphones and we demonstrate the effects of the directivity responses on beamforming using the minimum-variance distortionless response (MVDR) beamformer as an example. Our results show that the beamforming output can be degraded considerably if the microphone responses are not considered in the beamformer design.","PeriodicalId":218921,"journal":{"name":"2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123332171","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: 15
Joint dereverberation and noise reduction based on acoustic multichannel equalization 基于声学多通道均衡的联合去噪降噪方法
2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC) Pub Date : 2014-09-01 DOI: 10.1109/IWAENC.2014.6953354
I. Kodrasi, S. Doclo
{"title":"Joint dereverberation and noise reduction based on acoustic multichannel equalization","authors":"I. Kodrasi, S. Doclo","doi":"10.1109/IWAENC.2014.6953354","DOIUrl":"https://doi.org/10.1109/IWAENC.2014.6953354","url":null,"abstract":"In many speech communication applications, the recorded microphone signals are often corrupted by both reverberation and noise, which can significantly impair speech quality and intelligibility. While acoustic multichannel equalization techniques can achieve a high dereverberation performance, they may lead to amplification of the additive noise, since the equalization filters are typically designed without taking the presence of noise into account. This paper presents a novel approach to joint dereverberation and noise reduction based on acoustic multichannel equalization (DeNoREq). DeNoREq produces a weighted minimum mean-square error estimate of the clean speech signal, where the weighting parameter trades off between dereverberation and noise reduction performance. Furthermore, an automatic procedure for the selection of the weighting parameter is established. Experimental results for perfectly and erroneously estimated room impulse responses illustrate the effectiveness of the proposed technique in achieving a high dereverberation and noise reduction performance.","PeriodicalId":218921,"journal":{"name":"2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115276032","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
An automatic model-building algorithm for sparse approximation of room impulse responses with Orthonormal Basis Functions 一种基于正交基函数的房间脉冲响应稀疏逼近的自动建模算法
2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC) Pub Date : 2014-09-01 DOI: 10.1109/IWAENC.2014.6954296
Giacomo Vairetti, T. Waterschoot, M. Moonen, M. Catrysse, S. H. Jensen
{"title":"An automatic model-building algorithm for sparse approximation of room impulse responses with Orthonormal Basis Functions","authors":"Giacomo Vairetti, T. Waterschoot, M. Moonen, M. Catrysse, S. H. Jensen","doi":"10.1109/IWAENC.2014.6954296","DOIUrl":"https://doi.org/10.1109/IWAENC.2014.6954296","url":null,"abstract":"Orthonormal Basis Function (OBF) models are used to define stable fixed-poles infinite impulse response filter structures that allow to incorporate knowledge about the resonant characteristics of a stable, causal and linear system. In the approximation of a room impulse response, OBF models can include knowledge about the room resonances as a set of poles, which appear nonlinearly in the structure. A novel algorithm is pro-posed, that avoids this nonlinear problem by iteratively estimating the poles and building the model. Some of the properties of OBF models, such as orthogonality and linearity-in-the-parameters, are exploited and the final model has the favorable property of being scalable. The OBF model provides a longer response than the all-zero model and is particularly suited in approximating the early response and the predominant resonances for relatively small model orders.","PeriodicalId":218921,"journal":{"name":"2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC)","volume":"4323 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116817239","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
Multichannel dereverberation for hearing aids with interaural coherence preservation 保留耳间相干的助听器多声道去噪
2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC) Pub Date : 2014-09-01 DOI: 10.1109/IWAENC.2014.6953351
Sebastian Braun, Matteo Torcoli, Daniel Marquardt, Emanuël Habets, S. Doclo
{"title":"Multichannel dereverberation for hearing aids with interaural coherence preservation","authors":"Sebastian Braun, Matteo Torcoli, Daniel Marquardt, Emanuël Habets, S. Doclo","doi":"10.1109/IWAENC.2014.6953351","DOIUrl":"https://doi.org/10.1109/IWAENC.2014.6953351","url":null,"abstract":"Dereverberation for multichannel hearing aids is still a field of extensive research. If a single desired source is assumed, many binaural spatial filtering techniques such as the minimum variance distortionless response beamformer or the rank-one multichannel Wiener filter (MWF) distort the binaural cues of the residual undesired signal components. A recently proposed spatial filter minimizes the mean squared error plus an additional cost function to preserve the longterm interaural coherence of a diffuse noise field between the hearing aid signals. In this paper, we adapt this approach to binaural dereverberation by modeling the reverberation as a time-varying diffuse sound field. Using this approach, a considerable amount of reverberation and noise reduction can be achieved. Experimental results show that we can preserve the coherence at the output without significantly impairing the reverberation and noise reduction performance.","PeriodicalId":218921,"journal":{"name":"2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129143625","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: 13
Validation of realistic acoustic environments for listening tests using directional hearing aids 使用定向助听器进行听力测试的真实声学环境验证
2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC) Pub Date : 2014-09-01 DOI: 10.1109/IWAENC.2014.6954004
Chris Oreinos, J. Buchholz
{"title":"Validation of realistic acoustic environments for listening tests using directional hearing aids","authors":"Chris Oreinos, J. Buchholz","doi":"10.1109/IWAENC.2014.6954004","DOIUrl":"https://doi.org/10.1109/IWAENC.2014.6954004","url":null,"abstract":"Assessing the real-life benefit of hearing devices inside realistic acoustic environments (RAEs) has long been desired. However, no verified methods exist in literature. This study compares the short-time SNRbenefit provided by two multi-microphone directional hearing aid strategies (fixed cardioid & binaural beamformer) operating inside: (1) a real room; (2) the real room environment generated using room acoustics modelling; (3) the real room environment reconstructed using a 4/7 Mixed-Order Ambisonics system. The modelled RAE (2), compared to the real room (1), incurs small median SNRbenefit errors (<;2 dB), although the short-time errors are much larger (up to ±10 dB). The Ambisonics-coded RAE (3), compared to the modelled RAE (2), incurs smaller median errors (<;1 dB), while also preserving the short-time values remarkably well. The encouraging results require experimental verification with subjective measures (e.g., speech reception threshold benefit).","PeriodicalId":218921,"journal":{"name":"2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC)","volume":"26 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132546232","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: 7
Investigation of self-masking effects for the evaluation of in-car communication systems 车载通信系统评价中的自掩蔽效应研究
2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC) Pub Date : 2014-09-01 DOI: 10.1109/IWAENC.2014.6954302
Anne Theiss, G. Schmidt
{"title":"Investigation of self-masking effects for the evaluation of in-car communication systems","authors":"Anne Theiss, G. Schmidt","doi":"10.1109/IWAENC.2014.6954302","DOIUrl":"https://doi.org/10.1109/IWAENC.2014.6954302","url":null,"abstract":"The communication situation inside a passenger compartment can be impaired due to a high background noise at higher ve-locities. An In-Car Communication system (ICC system) is capable of improving this situation by recording the speech signal and reproducing the enhanced speech signal via the integrated loudspeakers. Due to this playback the speech level at the ears of listening passenger is increased but the signal is also fed back to the talking passenger. This might be disturbing for the talking passenger and hence might also be a quality issue of an ICC system. Up to now, the impact of this effect is not entirely clear and has not been investigated in detail yet. This contribution gives a first glance on this self-masking effect. Therefore, a psycho-acoustic experiment with test persons is presented in which these subjects should define in various scenarios, if the feedback is audible or even disturbing. The parameters of a scenario such as the delay of the feedback, the frequency range, and the current background noise are varied. Finally, the effect of the different parameters on the talking passenger and the impact on the quality of an ICC system is investigated.","PeriodicalId":218921,"journal":{"name":"2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126459965","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
Relaxed disjointness based clustering for joint blind source separation and dereverberation 基于松弛不连接的联合盲源分离与去噪聚类
2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC) Pub Date : 2014-09-01 DOI: 10.1109/IWAENC.2014.6954300
N. Ito, S. Araki, Takuya Yoshioka, T. Nakatani
{"title":"Relaxed disjointness based clustering for joint blind source separation and dereverberation","authors":"N. Ito, S. Araki, Takuya Yoshioka, T. Nakatani","doi":"10.1109/IWAENC.2014.6954300","DOIUrl":"https://doi.org/10.1109/IWAENC.2014.6954300","url":null,"abstract":"We propose a novel clustering technique based on a relaxed disjointness assumption for joint blind source separation (BSS) and dere-verberation. A disjointness assumption in conventional clustering techniques for BSS is that, at each time-frequency point, observed mixtures consist of a single source only. However, this is not the case in reverberant environments, which causes the performance of the conventional techniques to degrade. To deal with reverberant environments, we introduce a relaxed disjointness assumption: at each time-frequency point, dereverberated mixtures consist of a single source only. Under this assumption, the proposed algorithm alternates dereverberation and clustering-based source separation it-eratively, where clustering is performed on dereverberated mixtures. This algorithm is derived based on maximum a posteriori (MAP) fitting of a probabilistic generative model to observed reverberant mixtures. In experiments, the proposed method outperformed a state-of-the-art clustering technique in terms of a signal-to-interference ratio (SIR) by 0.6-4 dB.","PeriodicalId":218921,"journal":{"name":"2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121660787","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: 46
The acoustic echo cancelation using blind source separation to reduce double-talk interference 采用盲源分离的方法消除回声,减少双音干扰
2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC) Pub Date : 2012-10-04 DOI: 10.1109/IWAENC.2014.6954311
Y. Sakai, M. Akhtar
{"title":"The acoustic echo cancelation using blind source separation to reduce double-talk interference","authors":"Y. Sakai, M. Akhtar","doi":"10.1109/IWAENC.2014.6954311","DOIUrl":"https://doi.org/10.1109/IWAENC.2014.6954311","url":null,"abstract":"An acoustic echo canceler (AEC) is often employed to remove the acoustic echoes generated in hands-free communication systems. The AEC cancels the acoustic echoes by approximating the echo-path with the use of an adaptive filter and subtracting the pseudo echoes generated by the filter from the observed signal. The conventional adaptive algorithm for updating the filter, however, fails in estimation of the echo-path during double-talk when both the acoustic echo and the near-end speech are observed. Recently it has been shown that the blind source separation (BSS) can be employed to perform the echo cancelation during the double-talk; however, the convergence speed is slower than that of the conventional method. In this paper, a system is proposed that combines the conventional AEC and BSS; essentially, BSS is employed as a preprocessor for the adaptive filter performing the echo cancelation. Simulation results show that the proposed system is effective for the echo-path estimation during the double-talk as well as during variation in the echo path.","PeriodicalId":218921,"journal":{"name":"2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114912279","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
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
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