Documents disponibles dans la collection

Blind speech separation / Shiba, Shoji

Public ISBD Titre : Blind speech separation Type de document : document électronique Auteurs : Shiba, Shoji, Auteur ; Lee, Te-Won, Auteur Editeur : Berlin : Springer Année de publication : 2007 Collection : Signals and communication technology ISBN/ISSN/EAN : 978-1-402-06479-1 Langues : Anglais (eng) Mots-clés : Télécommunication  Engineering  Signal,  Image  and  Speech  Processing Résumé : This is the first book to provide a cutting edge reference to the fascinating topic of blind source separation (BSS) for convolved speech mixtures. Through contributions by the foremost experts on the subject, the book provides an up-to-date account of research findings, explains the underlying theory, and discusses potential applications. The individual chapters are designed to be tutorial in nature with specific emphasis on an in-depth treatment of state of the art techniques. Blind Speech Separation is divided into three parts: Part 1 presents overdetermined or critically determined BSS. Here the main technology is independent component analysis (ICA). ICA is a statistical method for extracting mutually independent sources from their mixtures. This approach utilizes spatial diversity to discriminate between desired and undesired components, i.e., it reduces the undesired components by forming a spatial null towards them. It is, in fact, a blind adaptive beamformer realized by unsupervised adaptive filtering. Part 2 addresses underdetermined BSS, where there are fewer microphones than source signals. Here, the sparseness of speech sources is very useful; we can utilize time-frequency diversity, where sources are active in different regions of the time-frequency plane. Part 3 presents monaural BSS where there is only one microphone. Here, we can separate a mixture by using the harmonicity and temporal structure of the sources. We can build a probabilistic framework by assuming a source model, and separate a mixture by maximizing the a posteriori probability of the sources. Blind speech separation [document électronique] / Shiba, Shoji, Auteur ; Lee, Te-Won, Auteur . - Springer, 2007. - (Signals and communication technology) . ISBN : 978-1-402-06479-1 Langues : Anglais (eng) Mots-clés : Télécommunication  Engineering  Signal,  Image  and  Speech  Processing Résumé : This is the first book to provide a cutting edge reference to the fascinating topic of blind source separation (BSS) for convolved speech mixtures. Through contributions by the foremost experts on the subject, the book provides an up-to-date account of research findings, explains the underlying theory, and discusses potential applications. The individual chapters are designed to be tutorial in nature with specific emphasis on an in-depth treatment of state of the art techniques. Blind Speech Separation is divided into three parts: Part 1 presents overdetermined or critically determined BSS. Here the main technology is independent component analysis (ICA). ICA is a statistical method for extracting mutually independent sources from their mixtures. This approach utilizes spatial diversity to discriminate between desired and undesired components, i.e., it reduces the undesired components by forming a spatial null towards them. It is, in fact, a blind adaptive beamformer realized by unsupervised adaptive filtering. Part 2 addresses underdetermined BSS, where there are fewer microphones than source signals. Here, the sparseness of speech sources is very useful; we can utilize time-frequency diversity, where sources are active in different regions of the time-frequency plane. Part 3 presents monaural BSS where there is only one microphone. Here, we can separate a mixture by using the harmonicity and temporal structure of the sources. We can build a probabilistic framework by assuming a source model, and separate a mixture by maximizing the a posteriori probability of the sources.

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité	Etat_Exemplaire
E00163	681.3 SHI	Ressources électroniques	Bibliothèque Centrale	Informatique	Disponible
E00164	681.3 SHI	Ressources électroniques	Bibliothèque Centrale	Informatique	Disponible

Advanced man-machine interaction / Kraiss, Karl-Friedrich

Public ISBD Titre : Advanced man-machine interaction Type de document : document électronique Auteurs : Kraiss, Karl-Friedrich, Auteur Editeur : Berlin : Springer Année de publication : 2007 Collection : Signals and communication technology ISBN/ISSN/EAN : 978-3-540-30619-1 Note générale : Configuration requise : Adobe acrobat Langues : Anglais (eng) Mots-clés : Engineering  Computer  science  Structural  control  (Engineering) Résumé : classification, and virtual environment implementation. In addition a test data base is included for gestures, head pose, facial expressions, full-body person recognition, and people tracking. These data are used for the examples throughout the book, but are also meant to encourage the reader to start experimentation on his own. Thus the book may serve as a self-contained introduction both for researchers and developers of man-machine interfaces. It may also be used for graduate-level university courses. Advanced man-machine interaction [document électronique] / Kraiss, Karl-Friedrich, Auteur . - Springer, 2007. - (Signals and communication technology) . ISBN : 978-3-540-30619-1 Configuration requise : Adobe acrobat Langues : Anglais (eng) Mots-clés : Engineering  Computer  science  Structural  control  (Engineering) Résumé : classification, and virtual environment implementation. In addition a test data base is included for gestures, head pose, facial expressions, full-body person recognition, and people tracking. These data are used for the examples throughout the book, but are also meant to encourage the reader to start experimentation on his own. Thus the book may serve as a self-contained introduction both for researchers and developers of man-machine interfaces. It may also be used for graduate-level university courses.

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité	Etat_Exemplaire
E00065	681.5 KRA	Ressources électroniques	Bibliothèque Centrale	Automatique	Disponible
E00066	681.5 KRA	Ressources électroniques	Bibliothèque Centrale	Automatique	Disponible

Acoustic MIMO signal processing / Huang , Yiteng

Public ISBD Titre : Acoustic MIMO signal processing Type de document : document électronique Auteurs : Huang , Yiteng, Auteur ; Benesty, Jacob, Auteur Editeur : Berlin : Springer Année de publication : 2007 Collection : Signals and communication technology ISBN/ISSN/EAN : 978-3-540-37630-9 Langues : Anglais (eng) Mots-clés : Acoustic  Channel  Identification  -  Acoustic  Signal  Processing  -  Adaptive  Systems  -  Audio  Processing  -  MIMO  Systems  -  Speech  Acquisition  and  Enhancement  -  Speech  Enhancement Résumé : Telecommunication systems and human-machine interfaces have begun using multiple microphones and loudspeakers to render interaction more lifelike, and more efficient. This raises acoustic signal processing problems under multiple-input multiple-output (MIMO) scenarios, encompassing distant speech acquisition, sound source localization and tracking, echo and noise control, source separation and speech dereverberation, and many others. The book opens with an acoustic MIMO paradigm, establishing fundamentals, and linking acoustic MIMO signal processing with classical signal processing and communication theories. The second part of this presents a novel analysis of acoustic applications carried out in the paradigm to reinforce the fundamentals of acoustic MIMO signal processing. Note de contenu : Introduction.- Part I: Theory.- Acoustic MIMO Systems.- Wiener Filter and Basic Adaptive Algorithms.- Sparse Adaptive Filters.- Frequency-Domain Adaptive Filters.- Blind Identification of Acoustic MIMO Systems.- Separation and Suppression of Co-Channel and Temporal Interference.- Part II: Applications.- Acoustic Echo Cancellation and Audio Bridging.- Time Delay Estimation and Acoustic Source Localization.- Speech Enhancement and Noise Reduction.- Source Separation and Speech Deverberation. ISBN 13 : 978-3540376309 Acoustic MIMO signal processing [document électronique] / Huang , Yiteng, Auteur ; Benesty, Jacob, Auteur . - Springer, 2007. - (Signals and communication technology) . ISBN : 978-3-540-37630-9 Langues : Anglais (eng) Mots-clés : Acoustic  Channel  Identification  -  Acoustic  Signal  Processing  -  Adaptive  Systems  -  Audio  Processing  -  MIMO  Systems  -  Speech  Acquisition  and  Enhancement  -  Speech  Enhancement Résumé : Telecommunication systems and human-machine interfaces have begun using multiple microphones and loudspeakers to render interaction more lifelike, and more efficient. This raises acoustic signal processing problems under multiple-input multiple-output (MIMO) scenarios, encompassing distant speech acquisition, sound source localization and tracking, echo and noise control, source separation and speech dereverberation, and many others. The book opens with an acoustic MIMO paradigm, establishing fundamentals, and linking acoustic MIMO signal processing with classical signal processing and communication theories. The second part of this presents a novel analysis of acoustic applications carried out in the paradigm to reinforce the fundamentals of acoustic MIMO signal processing. Note de contenu : Introduction.- Part I: Theory.- Acoustic MIMO Systems.- Wiener Filter and Basic Adaptive Algorithms.- Sparse Adaptive Filters.- Frequency-Domain Adaptive Filters.- Blind Identification of Acoustic MIMO Systems.- Separation and Suppression of Co-Channel and Temporal Interference.- Part II: Applications.- Acoustic Echo Cancellation and Audio Bridging.- Time Delay Estimation and Acoustic Source Localization.- Speech Enhancement and Noise Reduction.- Source Separation and Speech Deverberation. ISBN 13 : 978-3540376309

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité	Etat_Exemplaire
E00130	621.391 HUA	Ressources électroniques	Bibliothèque Centrale	Electronique	Disponible
E00129	621.391 HUA	Ressources électroniques	Bibliothèque Centrale	Electronique	Disponible