Adversarial Generative NMF for Single Channel Source Separation

• URL: http://arxiv.org/abs/2305.01758v1
• Date: Mon, 24 Apr 2023 09:26:43 GMT
• Title: Adversarial Generative NMF for Single Channel Source Separation
• Authors: Martin Ludvigsen and Markus Grasmair
• Abstract summary: We will apply this idea to the problem of source separation by means of non-negative matrix factorization (NMF) We show in numerical experiments, both for image and audio separation, that this leads to a clear improvement of the reconstructed signals.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The idea of adversarial learning of regularization functionals has recently been introduced in the wider context of inverse problems. The intuition behind this method is the realization that it is not only necessary to learn the basic features that make up a class of signals one wants to represent, but also, or even more so, which features to avoid in the representation. In this paper, we will apply this approach to the problem of source separation by means of non-negative matrix factorization (NMF) and present a new method for the adversarial training of NMF bases. We show in numerical experiments, both for image and audio separation, that this leads to a clear improvement of the reconstructed signals, in particular in the case where little or no strong supervision data is available.

Related papers

• Inverse-RLignment: Inverse Reinforcement Learning from Demonstrations for LLM Alignment [62.05713042908654]
  We introduce Alignment from Demonstrations (AfD), a novel approach leveraging high-quality demonstration data to overcome these challenges. We formalize AfD within a sequential decision-making framework, highlighting its unique challenge of missing reward signals. Practically, we propose a computationally efficient algorithm that extrapolates over a tailored reward model for AfD.
  arXiv  Detail & Related papers  (2024-05-24T15:13:53Z)
• Maximum Discrepancy Generative Regularization and Non-Negative Matrix Factorization for Single Channel Source Separation [0.0]
  In this paper, we will apply the idea of adversarial learning of regularization functionals to the training of generative models. We show in numerical experiments, both for image and audio separation, that this leads to a clear improvement of the reconstructed signals.
  arXiv  Detail & Related papers  (2024-03-26T15:16:01Z)
• Learning Invariant Molecular Representation in Latent Discrete Space [52.13724532622099]
  We propose a new framework for learning molecular representations that exhibit invariance and robustness against distribution shifts. Our model achieves stronger generalization against state-of-the-art baselines in the presence of various distribution shifts.
  arXiv  Detail & Related papers  (2023-10-22T04:06:44Z)
• Federated Representation Learning via Maximal Coding Rate Reduction [109.26332878050374]
  We propose a methodology to learn low-dimensional representations from a dataset that is distributed among several clients. Our proposed method, which we refer to as FLOW, utilizes MCR2 as the objective of choice, hence resulting in representations that are both between-class discriminative and within-class compressible.
  arXiv  Detail & Related papers  (2022-10-01T15:43:51Z)
• Invariant Causal Mechanisms through Distribution Matching [86.07327840293894]
  In this work we provide a causal perspective and a new algorithm for learning invariant representations. Empirically we show that this algorithm works well on a diverse set of tasks and in particular we observe state-of-the-art performance on domain generalization.
  arXiv  Detail & Related papers  (2022-06-23T12:06:54Z)
• Adaptive Weighted Nonnegative Matrix Factorization for Robust Feature Representation [9.844796520630522]
  Nonnegative matrix factorization (NMF) has been widely used to dimensionality reduction in machine learning. Traditional NMF does not properly handle outliers, so that it is sensitive to noise. This paper proposes an adaptive weighted NMF, which introduces weights to emphasize the different importance of each data point.
  arXiv  Detail & Related papers  (2022-06-07T05:27:08Z)
• Finding Rule-Interpretable Non-Negative Data Representation [2.817412580574242]
  We present a version of the NMF approach that merges rule-based descriptions with advantages of part-based representation. The proposed approach provides numerous advantages in tasks such as focused embedding or performing supervised multi-label NMF.
  arXiv  Detail & Related papers  (2022-06-03T10:20:46Z)
• Feature Weighted Non-negative Matrix Factorization [92.45013716097753]
  We propose the Feature weighted Non-negative Matrix Factorization (FNMF) in this paper. FNMF learns the weights of features adaptively according to their importances. It can be solved efficiently with the suggested optimization algorithm.
  arXiv  Detail & Related papers  (2021-03-24T21:17:17Z)
• FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs [53.710405006523274]
  This work focuses on the representation learning question: how can we learn such features? Under the assumption that the underlying (unknown) dynamics correspond to a low rank transition matrix, we show how the representation learning question is related to a particular non-linear matrix decomposition problem. We develop FLAMBE, which engages in exploration and representation learning for provably efficient RL in low rank transition models.
  arXiv  Detail & Related papers  (2020-06-18T19:11:18Z)
• Sparse Separable Nonnegative Matrix Factorization [22.679160149512377]
  We propose a new variant of nonnegative matrix factorization (NMF) Separability requires that the columns of the first NMF factor are equal to columns of the input matrix, while sparsity requires that the columns of the second NMF factor are sparse. We prove that, in noiseless settings and under mild assumptions, our algorithm recovers the true underlying sources.
  arXiv  Detail & Related papers  (2020-06-13T03:52:29Z)
• Theory inspired deep network for instantaneous-frequency extraction and signal components recovery from discrete blind-source data [1.6758573326215689]
  This paper is concerned with the inverse problem of recovering the unknown signal components, along with extraction of their frequencies. None of the existing decomposition methods and algorithms is capable of solving this inverse problem. We propose a synthesis of a deep neural network, based directly on a discrete sample set, that may be non-uniformly sampled, of the blind-source signal.
  arXiv  Detail & Related papers  (2020-01-31T18:54:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.