Informed Source Separation of Linear Instantaneous Under-Determined Audio Mixtures by Source Index Embedding

Parvaix, Mathieu; Girin, Laurent

doi:10.1109/tasl.2010.2097250

Cited by 34 publications

(54 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In direct consequence of this aspect, the estimated spectra of the source signals with a low SIR exhibit audibly missing spectral components, which may deteriorate the quality of the listening experience. The same effect but in a much more extreme manner was already observed with regard to the work in [1] and illustrated in [3]. The approach presented herein stands in marked contrast to the aforementioned techniques, first, because it exploits spatial diversity, and second, because it constrains the output to have a desired power level in order to overcome the issue of spectral gaps.…”

Section: Introductionmentioning

confidence: 52%

“…The following two algorithms were compared against each other: the USSR algorithm and an in-house implementation of the algorithm described in [1]. These algorithms were already compared in [3], but this time the USSR algorithm is served in three different flavors.…”

Section: A Algorithms Under Testmentioning

confidence: 99%

“…The reference ISS algorithm from [1]. USSR-A The iterative USSR algorithm [3] with pairwise extraction.…”

Section: Issamentioning

confidence: 99%

“…I N recent years several approaches have been proposed that address audio source separation in an "informed" scenario [1]- [3]. The reason for this new trend is the plain fact that after decades of research, "blind" or rather "semi-blind" source separation approaches to this day yield unsatisfactory quality with regard to what may be considered as "professional" audio applications, for which quality is key; for an overview and general concepts of blind approaches see [4].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Informed Audio Source Separation Using Linearly Constrained Spatial Filters

Gorlow

Marchand

2013

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Abstract-In this work we readdress the issue of audio source separation in an informed scenario, where certain information about the sound sources is embedded into their mixture as an imperceptible watermark. In doing so, we provide a description of an improved algorithm that follows the linearly constrained minimum-variance filtering approach in the subband domain, in order to obtain perceptually better estimates of the source signals in comparison to other published approaches. Just as its predecessor, the algorithm does not impose any restrictions on the number of simultaneously active sources, neither on their spectral overlap. It rather adapts to a given signal constellation and provides the best possible estimates under given constraints in linearithmic time. The validity of the approach is demonstrated on a stereo mixture with two levels of sound complexity. It is also shown by means of both objective and subjective evaluation that the proposed algorithm outperforms a reference algorithm by at least one grade. Bearing high perceptual resemblance to the original signals at a fairly tolerable data rate of 10-20 kbps per source, the algorithm hence seems well-suited for active listening applications such as re-mixing or re-spatialization in real time.Index Terms-Array signal processing, audio quality assessment, audio watermarking, informed audio source separation.

show abstract

Section: Introductionmentioning

confidence: 52%

Section: A Algorithms Under Testmentioning

confidence: 99%

“…The reference ISS algorithm from [1]. USSR-A The iterative USSR algorithm [3] with pairwise extraction.…”

Section: Issamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Informed Audio Source Separation Using Linearly Constrained Spatial Filters

Gorlow

Marchand

2013

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…This watermark helps the separation of a linear instantaneous monophonic mixture of four or five sources. In the stereophonic case, [16] proposed to embed the information about the mixture matrix and, for each molecule, the index of the zero, one, or two dominating sources in the molecule. At the receiver's end, thanks to this information, each molecule undergoes the separation process as a (over)determined mixture.…”

Section: Introductionmentioning

confidence: 99%

Perceptually controlled doping for audio source separation

Mahé

Nadalin

Suyama

et al. 2014

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

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 overcome this difficulty in the case where the original sources are available before the mixing process, the informed source separation (ISS) embeds in the mixture a watermark, which information can help a further separation. Though powerful, this technique is generally specific to a particular mixing setup and may be compromised by an additional bitrate compression stage. Thus, instead of watermarking, we propose a 'doping' method that makes the time-frequency representation of each source more sparse, while preserving its audio quality. This method is based on an iterative decrease of the distance between the distribution of the signal and a target sparse distribution, under a perceptual constraint. We aim to show that the proposed approach is robust to audio coding and that the use of the sparsified signals improves the source separation, in comparison with the original sources. In this work, the analysis is made only in instantaneous mixtures and focused on voice sources.

show abstract

Spatial Manipulation of Musical Sound: Informed Source Separation and Respatialization

Marchand¹

2019

Current Research in Systematic Musicology

View full text Add to dashboard Cite

Informed Source Separation of Linear Instantaneous Under-Determined Audio Mixtures by Source Index Embedding

Abstract: To cite this version:Mathieu Parvaix, Laurent Girin.

Cited by 34 publications

References 22 publications

Informed Audio Source Separation Using Linearly Constrained Spatial Filters

Informed Audio Source Separation Using Linearly Constrained Spatial Filters

Perceptually controlled doping for audio source separation

Spatial Manipulation of Musical Sound: Informed Source Separation and Respatialization

Contact Info

Product

Resources

About