Descripción del título
Time-Domain Beamforming and...
Time-Domain Beamforming and Blind Source Separation addresses the problem of separating spontaneous multi-party speech by way of microphone arrays (beamformers) and adaptive signal processing techniques. While existing techniques require a Double-Talk Detector (DTD) that interrupts the adaptation when the target is active, the described method addresses the separation problem using continuous, uninterrupted adaptive algorithms. With this approach, algorithm development is much simpler since no detection mechanism needs to be designed and needs no threshold to be tuned. Also, performance can be improved due to the adaptation during periods of double-talk. The authors use two techniques to achieve these results: implicit beamforming, which requires the position of the target speaker to be known; and time-domain blind-source separation (BSS), which exploits second-order statistics of the source signals. In combination, beamforming and BSS can be used to develop novel algorithms. Emphasis is placed on the development of an algorithm that combines the benefits of both approaches. The book presents experimental results obtained with real in-car microphone recordings involving simultaneous speech of the driver and the co-driver. In addition, experiments with background noise have been carried out in order to assess the robustness of the considered methods in noisy conditions
Monografía
monografia Rebiun14480344 https://catalogo.rebiun.org/rebiun/record/Rebiun14480344 cr nn 008mamaa 100301s2009 xxu| s |||| 0|eng d 9780387688367 978-0-387-68836-7 10.1007/978-0-387-68836-7 doi UPVA 996887802703706 UAM 991007781037804211 UCAR 991007922560004213 CBUC 991004876650706711 UMO 109689 TTBM bicssc UYS bicssc TEC008000 bisacsh COM073000 bisacsh 621.382 23 Bourgeois, Julien Time-Domain Beamforming and Blind Source Separation Recurso electrónico-En línea] Speech Input in the Car Environment edited by Julien Bourgeois, Wolfgang Minker Boston, MA Springer US 2009 Boston, MA Boston, MA Springer US Approx. 200 p. digital Approx. 200 p. Lecture Notes in Electrical Engineering 1876-1100 3 Engineering (Springer-11647) Account for Random Microstructure in Multiscale Models -- Multiscale Modeling of Tensile Failure in Fiber-Reinforced Composites -- Adaptive Concurrent Multi-Level Model for Multiscale Analysis of Composite Materials Including Damage -- Multiscale and Multi-Level Modeling of Composites -- A Micro-Mechanics-Based Notion of Stress for use in the Determination of Continuum-Level Mechanical Properties via Molecular Dynamics -- Multiscale Modeling and Simulation of Deformation in Nanoscale Metallic Multilayered Composites -- Multiscale Modeling of Composites Using Analytical Methods -- Nested Nonlinear Multiscale Frameworks for the Analysis of Thick-Section Composite Materials and Sructures -- Predicting Thermooxidative Degradation and Performance of High-Temperature Polymer Matrix Composites -- Modeling of Stiffness, Strength, and Structure-Property Relationship in Crosslinked Silica Aerogel -- Multiscale Modeling of the Evolution of Damage in Heterogeneous Viscoelastic Solids -- Multiscale Modeling for Damage Analysis -- Hierarchical Modeling of Deformation of Materials from the Atomic to the Continuum Scale Accesible sólo para usuarios de la UPV Recurso a texto completo Time-Domain Beamforming and Blind Source Separation addresses the problem of separating spontaneous multi-party speech by way of microphone arrays (beamformers) and adaptive signal processing techniques. While existing techniques require a Double-Talk Detector (DTD) that interrupts the adaptation when the target is active, the described method addresses the separation problem using continuous, uninterrupted adaptive algorithms. With this approach, algorithm development is much simpler since no detection mechanism needs to be designed and needs no threshold to be tuned. Also, performance can be improved due to the adaptation during periods of double-talk. The authors use two techniques to achieve these results: implicit beamforming, which requires the position of the target speaker to be known; and time-domain blind-source separation (BSS), which exploits second-order statistics of the source signals. In combination, beamforming and BSS can be used to develop novel algorithms. Emphasis is placed on the development of an algorithm that combines the benefits of both approaches. The book presents experimental results obtained with real in-car microphone recordings involving simultaneous speech of the driver and the co-driver. In addition, experiments with background noise have been carried out in order to assess the robustness of the considered methods in noisy conditions Reproducción electrónica Forma de acceso: Web Engineering Acoustics Computer engineering Telecommunication Engineering Signal, Image and Speech Processing Communications Engineering, Networks Acoustics Electrical Engineering Minker, Wolfgang SpringerLink (Servicio en línea) Springer eBooks Springer eBooks Printed edition 9780387688350 Lecture Notes in Electrical Engineering 1876-1100 3