Pub Date : 1900-01-01DOI: 10.1109/NNSP.2003.1318066
G. Costantini, D. Casali, A. Uncini
In this paper we propose a method to simulate a 3D acoustical environment in which sound sources are positioned in well defined sides. Our method is real-time applications oriented, due to the low computational cost of the implemented operations. The spatial position that the human brain assigns to a sound is influenced mainly by the differences between the sound signals that reach the listener's ears, related to the sound source angulation with respect to the listener's head. The reverberation effect, on the other side, depends on the type of environment. All this elements have to be simulated in order to give the illusion that a sound comes from a particular position in a particular environment. To obtain this result, we perform a suitable sound processing, that can be separated in two main tasks: reverberation and spatialization. The first one is mainly related to the environment itself: it depends on the shape of the environment and on the absorption coefficients of the walls. This is the most computational intensive component, if we want to reproduce it accurately, so we approximate it by an adaptive IIR filter. By the spatialization, the listener hears the sound as coming from a particular direction. This task, carried out by using the head related transfer functions (HRTFs), has to be applied to every sound source differently.
{"title":"Adaptive room acoustic response simulation: a virtual 3D application","authors":"G. Costantini, D. Casali, A. Uncini","doi":"10.1109/NNSP.2003.1318066","DOIUrl":"https://doi.org/10.1109/NNSP.2003.1318066","url":null,"abstract":"In this paper we propose a method to simulate a 3D acoustical environment in which sound sources are positioned in well defined sides. Our method is real-time applications oriented, due to the low computational cost of the implemented operations. The spatial position that the human brain assigns to a sound is influenced mainly by the differences between the sound signals that reach the listener's ears, related to the sound source angulation with respect to the listener's head. The reverberation effect, on the other side, depends on the type of environment. All this elements have to be simulated in order to give the illusion that a sound comes from a particular position in a particular environment. To obtain this result, we perform a suitable sound processing, that can be separated in two main tasks: reverberation and spatialization. The first one is mainly related to the environment itself: it depends on the shape of the environment and on the absorption coefficients of the walls. This is the most computational intensive component, if we want to reproduce it accurately, so we approximate it by an adaptive IIR filter. By the spatialization, the listener hears the sound as coming from a particular direction. This task, carried out by using the head related transfer functions (HRTFs), has to be applied to every sound source differently.","PeriodicalId":315958,"journal":{"name":"2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127930134","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}
Pub Date : 1900-01-01DOI: 10.1109/NNSP.2003.1318086
R. Ferrari, C. Panazio, R. Attux, C. Cavalcante, L. Castro, F. V. Zuben, J. Romano
Ee present a new paradigm for unsupervised nonlinear equalization based on prediction-error fuzzy filters. Tests in different linear channel scenarios are carried out in order to assess the performance of the equalizer. The results show that the proposal is solid and may provide a performance close to that of a Bayesian equalizer.
{"title":"Unsupervised channel equalization using fuzzy prediction-error filters","authors":"R. Ferrari, C. Panazio, R. Attux, C. Cavalcante, L. Castro, F. V. Zuben, J. Romano","doi":"10.1109/NNSP.2003.1318086","DOIUrl":"https://doi.org/10.1109/NNSP.2003.1318086","url":null,"abstract":"Ee present a new paradigm for unsupervised nonlinear equalization based on prediction-error fuzzy filters. Tests in different linear channel scenarios are carried out in order to assess the performance of the equalizer. The results show that the proposal is solid and may provide a performance close to that of a Bayesian equalizer.","PeriodicalId":315958,"journal":{"name":"2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114266368","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}
Pub Date : 1900-01-01DOI: 10.1109/NNSP.2003.1318074
L. M. San-José-Revuelta, Jesús Cid-Sueiro
This work presents two different algorithms for multiuser detection in wireless DS/CDMA environments. First, a Bayesian detector which implements merging techniques, based on natural computation selection strategies, for complexity limitation, is analyzed, and, second, a low complexity radial basis function-based detector is presented. Both approaches share in common a low computational load and the capability to be implemented even with a high number of active users, since their complexity does not increase exponentially with it. Their performance and characteristics are compared with those of traditional multiuser detectors, such as the matched filter, the decorrelator and the MMSE detector, as well as with other low complexity detectors based on evolutionary computation methods.
{"title":"Bayesian and RBF structures for wireless communications detection","authors":"L. M. San-José-Revuelta, Jesús Cid-Sueiro","doi":"10.1109/NNSP.2003.1318074","DOIUrl":"https://doi.org/10.1109/NNSP.2003.1318074","url":null,"abstract":"This work presents two different algorithms for multiuser detection in wireless DS/CDMA environments. First, a Bayesian detector which implements merging techniques, based on natural computation selection strategies, for complexity limitation, is analyzed, and, second, a low complexity radial basis function-based detector is presented. Both approaches share in common a low computational load and the capability to be implemented even with a high number of active users, since their complexity does not increase exponentially with it. Their performance and characteristics are compared with those of traditional multiuser detectors, such as the matched filter, the decorrelator and the MMSE detector, as well as with other low complexity detectors based on evolutionary computation methods.","PeriodicalId":315958,"journal":{"name":"2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129306649","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}
Pub Date : 1900-01-01DOI: 10.1109/NNSP.2003.1318071
N. Ikoma, Yasutake Miyahara, H. Maeda
Causal estimation of multiple feature points trajectories by using a switching state space model is proposed. The state vector of the model consists of the position of each feature point, the velocity of each rigid object, and some indicator variables for each feature point. Ther are two types of indicator variables: an object indicator representing the association between the feature point and rigid object, and an aperture indicator representing the attribute of the point, e.g. aperture or not. By estimating the state vector using a Rao-Blackwellized particle filter, smooth trajectories of feature points, velocity of objects, object indicators, and aperture indicators are obtained simultaneously. Performance on a real image sequence is presented by comparing to a Kalman filter being given true indicators.
{"title":"Tracking of feature points in a scene of moving rigid objects by Bayesian switching structure model with particle filter","authors":"N. Ikoma, Yasutake Miyahara, H. Maeda","doi":"10.1109/NNSP.2003.1318071","DOIUrl":"https://doi.org/10.1109/NNSP.2003.1318071","url":null,"abstract":"Causal estimation of multiple feature points trajectories by using a switching state space model is proposed. The state vector of the model consists of the position of each feature point, the velocity of each rigid object, and some indicator variables for each feature point. Ther are two types of indicator variables: an object indicator representing the association between the feature point and rigid object, and an aperture indicator representing the attribute of the point, e.g. aperture or not. By estimating the state vector using a Rao-Blackwellized particle filter, smooth trajectories of feature points, velocity of objects, object indicators, and aperture indicators are obtained simultaneously. Performance on a real image sequence is presented by comparing to a Kalman filter being given true indicators.","PeriodicalId":315958,"journal":{"name":"2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126199118","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}
Pub Date : 1900-01-01DOI: 10.1109/NNSP.2003.1318065
R. Pichevar, J. Rouat
We use a two-layered unsupervised bio-inspired neural network to segregate sound sources, e.g. double-vowels or vowels intruded by nonstationary noise sources. The network consists of spiking neurons. The spiking neurons in both layers are modeled by relaxation oscillators. The first layer of the network is locally connected, while the second layer is a fully connected network. We show that in order to correctly segregate sound sources, we should either use Cochleotopic/AMtopic map (CAM) or Cochleotopic/Spectrotopic map (CSM) depending on the nature of the intruding sound source.
{"title":"Cochleotopic/AMtopic (CAM) and Cochleotopic/Spectrotopic (CSM) map based sound sourcce separation using relaxatio oscillatory neurons","authors":"R. Pichevar, J. Rouat","doi":"10.1109/NNSP.2003.1318065","DOIUrl":"https://doi.org/10.1109/NNSP.2003.1318065","url":null,"abstract":"We use a two-layered unsupervised bio-inspired neural network to segregate sound sources, e.g. double-vowels or vowels intruded by nonstationary noise sources. The network consists of spiking neurons. The spiking neurons in both layers are modeled by relaxation oscillators. The first layer of the network is locally connected, while the second layer is a fully connected network. We show that in order to correctly segregate sound sources, we should either use Cochleotopic/AMtopic map (CAM) or Cochleotopic/Spectrotopic map (CSM) depending on the nature of the intruding sound source.","PeriodicalId":315958,"journal":{"name":"2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122539701","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}
Pub Date : 1900-01-01DOI: 10.1109/NNSP.2003.1318064
Guoning Hu, Deliang Wang
Speech segregation from acoustic interference is a very challenging task. Previous systems have dealt with voiced speech with success, but they cannot handle unvoiced speech. We study the segregation of stop consonants, which contain significant unvoiced signals. We propose a novel method that employs onset as a major cue to segregate stop consonants. Our system first detects stops through onset detection and Bayesian classification of acoustic-phonetic features, and then performs grouping based on onset coincidence. The system has been tested and performs well on utterances mixed with various types of interference.
{"title":"Segregation of stop consonants from acoustic interference","authors":"Guoning Hu, Deliang Wang","doi":"10.1109/NNSP.2003.1318064","DOIUrl":"https://doi.org/10.1109/NNSP.2003.1318064","url":null,"abstract":"Speech segregation from acoustic interference is a very challenging task. Previous systems have dealt with voiced speech with success, but they cannot handle unvoiced speech. We study the segregation of stop consonants, which contain significant unvoiced signals. We propose a novel method that employs onset as a major cue to segregate stop consonants. Our system first detects stops through onset detection and Bayesian classification of acoustic-phonetic features, and then performs grouping based on onset coincidence. The system has been tested and performs well on utterances mixed with various types of interference.","PeriodicalId":315958,"journal":{"name":"2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122766796","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}
Pub Date : 1900-01-01DOI: 10.1109/NNSP.2003.1318079
T. Gautama, M. Hulle
An approach for testing the presence of Granger causality between two time series is proposed. The residue of the destination signal after self-prediction is computed, after which a cross-prediction of the source signal over this residue is examined. In the absence of causality, there should be no cross-predictive power, due to which the performance of the cross-prediction system can be used as an indication of causality. The proposed approach uses the surrogate data method, and implements the self- and cross-prediction systems as feedforward neural networks. It is tested on synthetic examples, and a sensitivity analysis demonstrates the robustness of the approach.
{"title":"Surrogate-based test for Granger causality","authors":"T. Gautama, M. Hulle","doi":"10.1109/NNSP.2003.1318079","DOIUrl":"https://doi.org/10.1109/NNSP.2003.1318079","url":null,"abstract":"An approach for testing the presence of Granger causality between two time series is proposed. The residue of the destination signal after self-prediction is computed, after which a cross-prediction of the source signal over this residue is examined. In the absence of causality, there should be no cross-predictive power, due to which the performance of the cross-prediction system can be used as an indication of causality. The proposed approach uses the surrogate data method, and implements the self- and cross-prediction systems as feedforward neural networks. It is tested on synthetic examples, and a sensitivity analysis demonstrates the robustness of the approach.","PeriodicalId":315958,"journal":{"name":"2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718)","volume":"8 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127374574","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}
Pub Date : 1900-01-01DOI: 10.1109/NNSP.2003.1318073
M. Delakis, C. Garcia
We present a face detection approach based on a convolutional neural architecture, designed to detect and precisely localize highly variable face patterns, in complex real world images. Our system automatically synthesizes simple problem-specific feature extractors from a training set of face and non face patterns, without making any assumptions or using any hand-made design concerning the features to extract or the areas of the face pattern to analyze. Experiments on different difficult test sets have shown that our approach provide superior overall detection results, while being computationally more efficient than most of state-of-the-art approaches that require dense scanning and local preprocessing.
{"title":"Training convolutional filters for robust face detection","authors":"M. Delakis, C. Garcia","doi":"10.1109/NNSP.2003.1318073","DOIUrl":"https://doi.org/10.1109/NNSP.2003.1318073","url":null,"abstract":"We present a face detection approach based on a convolutional neural architecture, designed to detect and precisely localize highly variable face patterns, in complex real world images. Our system automatically synthesizes simple problem-specific feature extractors from a training set of face and non face patterns, without making any assumptions or using any hand-made design concerning the features to extract or the areas of the face pattern to analyze. Experiments on different difficult test sets have shown that our approach provide superior overall detection results, while being computationally more efficient than most of state-of-the-art approaches that require dense scanning and local preprocessing.","PeriodicalId":315958,"journal":{"name":"2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718)","volume":"162 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121612112","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：