Singing-voice separation from monaural recordings using robust principal component analysis

By Po-Sen Huang, Scott Deeann Chen, Paris Smaragdis, Mark Hasegawa-Johnson. IEEE International Conference on Acoustics, Speech, and Signal Processing, 2012

362 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/f911d3e274aa01879fa1b5b1f2c3adfdbb9c0530

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

The 2018 Signal Separation Evaluation Campaign (2018, methodology): “They are: MELO as described in [24], as well as all the method implemented in NUSSL [15]: 2DFT [25], RPCA [9], REP1 [22], REP2 [20], HPSS [8].”
DEEP CLUSTERING AND CONVENTIONAL NETWORKS FOR MUSIC SEPARATION: STRONGER TOGETHER (2016, methodology): “Unsupervised methods, such as those based on computational auditory scene analysis (CASA) [4], source/filter modeling [5], or low-rank and sparse modeling [6], have difficulty in capturing the dynamics of the vocals and instruments, while supervised methods, such as those based on nonnegative matrix”
Multichannel Audio Source Separation With Deep Neural Networks (2016, methodology): “techniques based on the iterative expectation-maximization (EM) algorithm [3], robust principal component analysis (PCA) [14], or kernel additive modelling (KAM) [15].”
Multichannel music separation with deep neural networks (2016, neutral): “4 compares the performance of the proposed system to that of other techniques on the vocals (see [19] for the implementation details of all techniques): • Matrix factorization systems include OZE [15], DUR [28], and HUA [29]; • KAM { 1,2 } are variants of KAM [17]; • RAF { 1,2,3 } are variants of RE”
Deep learning for monaural speech separation (2014, background): “Separating singing voices from music enhances the accuracy of chord recognition [3].”
Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation (2015, background): “For example, in singing voice separation tasks, several approaches have been proposed to exploit the assumption of the low rank and sparsity of the music and speech signals, respectively [1], [3], [4], [5].”