• Publications
  • Influence
Multichannel Nonnegative Matrix Factorization in Convolutive Mixtures for Audio Source Separation
  • A. Ozerov, C. Févotte
  • Mathematics, Computer Science
  • IEEE Transactions on Audio, Speech, and Language…
  • 1 March 2010
TLDR
We consider inference in a general data-driven object-based model of multichannel audio data, assumed generated as a possibly underdetermined convolutive mixture of source signals. Expand
  • 551
  • 71
  • PDF
A General Flexible Framework for the Handling of Prior Information in Audio Source Separation
TLDR
We introduce a general audio source separation framework based on a library of structured source models that enable the incorporation of prior knowledge about each source via user-specifiable constraints. Expand
  • 283
  • 26
  • PDF
A Consolidated Perspective on Multimicrophone Speech Enhancement and Source Separation
TLDR
Speech enhancement and separation are core problems in audio signal processing, with commercial applications in devices as diverse as mobile phones, conference call systems, hands-free systems, or hearing aids. Expand
  • 234
  • 21
  • PDF
Multi-source TDOA estimation in reverberant audio using angular spectra and clustering
TLDR
We introduce and evaluate five new TDOA estimation methods inspired from signal-to-noise-ratio (SNR) weighting and probabilistic multi-source modeling techniques. Expand
  • 181
  • 16
  • PDF
Adaptation of Bayesian Models for Single-Channel Source Separation and its Application to Voice/Music Separation in Popular Songs
TLDR
We introduce a general formalism for source model adaptation which is expressed in the framework of Bayesian models, and further clarified in terms of a MAP adaptation criterion. Expand
  • 173
  • 13
  • PDF
Nonnegative matrix factorization and spatial covariance model for under-determined reverberant audio source separation
TLDR
We address the problem of blind audio source separation in the under-determined and convolutive case. Expand
  • 83
  • 9
  • PDF
Notes on Nonnegative Tensor Factorization of the Spectrogram for Audio Source Separation: Statistical Insights and Towards Self-Clustering of the Spatial Cues
TLDR
Nonnegative tensor factorization (NTF) of multichannel spectrograms under PARAFAC structure has recently been proposed by Fitzgerald et al as a mean of performing blind source separation. Expand
  • 58
  • 9
  • PDF
The signal separation evaluation campaign (2007-2010): Achievements and remaining challenges
TLDR
We present the outcomes of three recent evaluation campaigns in the field of audio and biomedical source separation. Expand
  • 148
  • 6
  • PDF
Multichannel nonnegative tensor factorization with structured constraints for user-guided audio source separation
TLDR
This paper considers multichannel audio source separation from convolutive mixtures, possibly underdetermined (more sources than sensors). Expand
  • 105
  • 6
  • PDF
On evaluating face tracks in movies
TLDR
We introduce and make publicly available a new dataset, based on the full annotation of a feature movie, to help fill this gap. Expand
  • 25
  • 6
...
1
2
3
4
5
...