Single channel source separation using time-frequency non-negative matrix factorization and sigmoid base normalization deep neural networks

DOI10.1007/S11045-022-00830-2MaRDI QIDQ2675487zbMATH OpenOpenAlexWikidataFDO

Authors Yannam Vasantha Koteswararao, C. B. Rama Rao

Publication date 23 September 2022

Published in Multidimensional Systems and Signal Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s11045-022-00830-2

zbMATH Keywords

deep neural networksinverse STFT operationshort term Fourier transformsigmoid base normalizationsoft masktime-frequency non-negative matrix factorization

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Recommendations

• Single channel informed signal separation using artificial-stereophonic mixtures and exemplar-guided matrix factor deconvolution
• Analysis of the convergence properties of self-normalized source separation neural networks
• New self-normalized blind source separation networks for instantaneous and convolutive mixtures
• Multimodal Soft Nonnegative Matrix Co-Factorization for Convolutive Source Separation
• Supervised non-negative matrix factorization for audio source separation
• Null Space Component Analysis of One-Shot Single-Channel Source Separation Problem
• Unsupervised Single-Channel Separation of Nonstationary Signals Using Gammatone Filterbank and Itakura–Saito Nonnegative Matrix Two-Dimensional Factorizations
• Independent Component Analysis and Blind Signal Separation
• Tensor factorisation for narrowband single channel source decomposition

Cites work

• A Family of Hybrid Analog–Digital Beamforming Methods for Massive MIMO Systems
• Hybrid Beamforming With Selection for Multiuser Massive MIMO Systems

Cited in

(4)

• Single channel informed signal separation using artificial-stereophonic mixtures and exemplar-guided matrix factor deconvolution
• Supervised determined source separation with multichannel variational autoencoder
• Evaluating single-channel speech separation performance in transform-domain
• Complex-valued temporal convolutional network for speech enhancement

This page was built for publication: Single channel source separation using time-frequency non-negative matrix factorization and sigmoid base normalization deep neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2675487)