Laplace Nonnegative Matrix Factorization with Application to Semi-supervised Audio Denoising

Tanji, Hiroki; Murakami, Takahiro; Kamata, Hiroyuki

doi:10.23919/eusipco.2019.8903074

Cited by 2 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various divergences have been proposed in the NMF literature [1,11,[14][15][16][17][18][19][20][21][22]. Of these, divergences [11,[15][16][17][18][19][20] that are generalized using hyper-parameters are promising because they allow the evaluation of various types of divergences in audio applications.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Multiplicative Update Algorithm for Nonnegative Matrix Factorization and Its Application to Audio Signals

Tanji

Murakami

2023

IEICE Trans. Fundamentals

View full text Add to dashboard Cite

The design and adjustment of the divergence in audio applications using nonnegative matrix factorization (NMF) is still open problem. In this study, to deal with this problem, we explore a representation of the divergence using neural networks (NNs). Instead of the divergence, our approach extends the multiplicative update algorithm (MUA), which estimates the NMF parameters, using NNs. The design of the extended MUA incorporates NNs, and the new algorithm is referred to as the deep MUA (DeMUA) for NMF. While the DeMUA represents the algorithm for the NMF, interestingly, the divergence is obtained from the incorporated NN.In addition, we propose theoretical guides to design the incorporated NN such that it can be interpreted as a divergence. By appropriately designing the NN, MUAs based on existing divergences with a single hyper-parameter can be represented by the DeMUA. To train the DeMUA, we applied it to audio denoising and supervised signal separation. Our experimental results show that the proposed architecture can learn the MUA and the divergences in sparse denoising and speech separation tasks and that the MUA based on generalized divergences with multiple parameters shows favorable performances on these tasks.

show abstract

Section: Introductionmentioning

confidence: 99%

“…The existing generalized divergences are flexible compared to divergences without a hyper-parameter (e.g., [1,14,21,22]). However, two problems remain unsolved.…”

Section: Introductionmentioning

confidence: 99%