N
Ngoc Q. K. Duong
Researcher at InterDigital, Inc.
Publications - 66
Citations - 1965
Ngoc Q. K. Duong is an academic researcher from InterDigital, Inc.. The author has contributed to research in topics: Source separation & Non-negative matrix factorization. The author has an hindex of 20, co-authored 65 publications receiving 1741 citations. Previous affiliations of Ngoc Q. K. Duong include French Institute for Research in Computer Science and Automation & University of Rennes.
Papers
More filters
Journal ArticleDOI
Under-Determined Reverberant Audio Source Separation Using a Full-Rank Spatial Covariance Model
TL;DR: In this article, the contribution of each source to all mixture channels in the time-frequency domain was modeled as a zero-mean Gaussian random variable whose covariance encodes the spatial characteristics of the source.
Posted Content
Under-determined reverberant audio source separation using a full-rank spatial covariance model
TL;DR: This paper addresses the modeling of reverberant recording environments in the context of under-determined convolutive blind source separation by model the contribution of each source to all mixture channels in the time-frequency domain as a zero-mean Gaussian random variable whose covariance encodes the spatial characteristics of the source.
Journal ArticleDOI
The signal separation evaluation campaign (2007-2010): Achievements and remaining challenges
Emmanuel Vincent,Shoko Araki,Fabian J. Theis,Guido Nolte,Pau Bofill,Hiroshi Sawada,Alexey Ozerov,B. Vikrham Gowreesunker,Dominik Lutter,Ngoc Q. K. Duong +9 more
TL;DR: The outcomes of three recent evaluation campaigns in the field of audio and biomedical source separation are presented and directions for future research and evaluation are proposed, based on the ideas raised during the related panel discussion at the Ninth International Conference on Latent Variable Analysis and Signal Separation.
Proceedings ArticleDOI
Nonnegative matrix factorization and spatial covariance model for under-determined reverberant audio source separation
Simon Arberet,Alexey Ozerov,Ngoc Q. K. Duong,Emmanuel Vincent,Rémi Gribonval,Frédéric Bimbot,Pierre Vandergheynst +6 more
TL;DR: This work addresses the problem of blind audio source separation in the under-determined and convolutive case by maximizing the likelihood of the mixture using an expectation-maximization (EM) algorithm.
Proceedings ArticleDOI
Audio Style Transfer
TL;DR: In this paper, a sound texture model is used to extract statistics characterizing the reference audio style, followed by an optimization-based audio texture synthesis to modify the target content, instead of random noise and the optimized loss is only about texture, not structure.