Sciweavers

506 search results - page 60 / 102
» icassp 2009
Sort
View
107
Voted
ICASSP
2009
IEEE
15 years 7 months ago
A watermarking-based method for single-channel audio source separation
In this paper, we address the issue of audio source separation with a single channel, i.e. the estimation of source signals from a single mixture of these signals. This problem is...
Mathieu Parvaix, Laurent Girin, Jean-Marc Brossier
ICASSP
2009
IEEE
15 years 7 months ago
Applying improved spectral modeling for High Quality voice conversion
In this work, accurate spectral envelope estimation is applied to Voice Conversion in order to achieve High-Quality timbre conversion. True-Envelope based estimators allow model o...
Fernando Villavicencio, Axel Röbel, Xavier Ro...
98
Voted
ICASSP
2009
IEEE
15 years 7 months ago
Blind system identification for speech dereverberation with Forced Spectral Diversity
The common zeros problem for blind system identification (BSI) is well known. It degrades the performance of classic BSI algorithms and therefore imposes the limit on the perform...
Xiang Lin, Andy W. H. Khong, Patrick A. Naylor
102
Voted
ICASSP
2009
IEEE
15 years 7 months ago
Robust and fast non asymmetric distributed source coding using turbo codes on the syndrome trellis
We consider the distributed compression of two (binary memoryless) correlated sources and propose a unique codec that can reach any point in the Slepian-Wolf region. In a previous...
Velotiaray Toto-Zarasoa, Aline Roumy, Christine Gu...
83
Voted
ICASSP
2009
IEEE
15 years 7 months ago
Incorporating prior knowledge on the digital media creation process into audio classifiers
In the process of music content creation, a wide range of typical audio effects such as reverberation, equalization or dynamic compression are very commonly used. Despite the fact...
Maxime Lardeur, Slim Essid, Gaël Richard, Mar...