Skip to main content

Informed Acoustic Source Separation

Acoustic source separation has received a great interest from the research community but the problem remains challenging in the undetermined setting (when the number of sources I is less than the number of channels J), including the single-channel case (I = 1), and for convolutive mixtures. It is now quite clear that source separation performances strongly depend on the amount of available prior information about the sources and the mixing process one can introduce in the source separation algorithm. The so-called informed source separation methods then appear to be particularly attractive.

This special issue will also build on the success of the recent (double) special session at Eusipco 2012 on the very same topic.

Edited by:  Ozerov Alexey,  Ali Taylan Cemgil, Derry FitzGerald, Gaël Richard and Tuomas Virtanen

  1. In this paper, we exploit the non-linear relation between a speech source and its associated lip video as a source of extra information to propose an improved audio-visual speech source separation (AVSS) algor...

    Authors: Alireza Kazemi, Reza Boostani and Fariborz Sobhanmanesh
    Citation: EURASIP Journal on Advances in Signal Processing 2014 2014:47
  2. This paper proposes a new method to enhance the performance of non-negative tensor factorization (NTF), one of the most prevalent source separation techniques nowadays. The enhancement is mainly achieved by in...

    Authors: Yuki Mitsufuji and Axel Roebel
    Citation: EURASIP Journal on Advances in Signal Processing 2014 2014:40
  3. The separation of an underdetermined audio mixture can be performed through sparse component analysis (SCA) that relies however on the strong hypothesis that source signals are sparse in some domain. To overco...

    Authors: Gaël Mahé, Everton Z Nadalin, Ricardo Suyama and João MT Romano
    Citation: EURASIP Journal on Advances in Signal Processing 2014 2014:27
  4. For speech enhancement or blind signal extraction (BSE), estimating interference and noise characteristics is decisive for its performance. For multichannel approaches using multiple microphone signals, a BSE ...

    Authors: Yuanhang Zheng, Klaus Reindl and Walter Kellermann
    Citation: EURASIP Journal on Advances in Signal Processing 2014 2014:26
  5. We present a system for the automatic separation of solo instruments and music accompaniment in polyphonic music recordings. Our approach is based on a pitch detection front-end and a tone-based spectral estim...

    Authors: Estefanía Cano, Gerald Schuller and Christian Dittmar
    Citation: EURASIP Journal on Advances in Signal Processing 2014 2014:23
  6. A recent trend in hearing aids is the connection of the left and right devices to collaborate between them. Binaural systems can provide natural binaural hearing and support the improvement of speech intelligi...

    Authors: David Ayllón, Roberto Gil-Pita and Manuel Rosa-Zurera
    Citation: EURASIP Journal on Advances in Signal Processing 2013 2013:187
  7. Close-microphone techniques are extensively employed in many live music recordings, allowing for interference rejection and reducing the amount of reverberation in the resulting instrument tracks. However, des...

    Authors: Julio J Carabias-Orti, Máximo Cobos, Pedro Vera-Candeas and Francisco J Rodríguez-Serrano
    Citation: EURASIP Journal on Advances in Signal Processing 2013 2013:184
  8. We consider the Gaussian framework for reverberant audio source separation, where the sources are modeled in the time-frequency domain by their short-term power spectra and their spatial covariance matrices. W...

    Authors: Ngoc Q K Duong, Emmanuel Vincent and Rémi Gribonval
    Citation: EURASIP Journal on Advances in Signal Processing 2013 2013:149