Audio Source Separation

Description

This book provides the first comprehensive overview of the fascinating topic of audio source separation based on non-negative matrix factorization, deep neural networks, and sparse component analysis. The first section of the book covers single channel source separation based on non-negative matrix factorization (NMF). After an introduction to the technique, two further chapters describe separation of known sources using non-negative spectrogram factorization, and temporal NMF models. In section two, NMF methods are extended to multi-channel source separation. Section three introduces deep neural network (DNN) techniques, with chapters on multichannel and single channel separation, and a further chapter on DNN based mask estimation for monaural speech separation. In section four, sparse component analysis (SCA) is discussed, with chapters on source separation using audio directional statistics modelling, multi-microphone MMSE-based techniques and diffusion map methods. The book brings together leading researchers to provide tutorial-like and in-depth treatments on major audio source separation topics, with the objective of becoming the definitive source for a comprehensive, authoritative, and accessible treatment. This book is written for graduate students and researchers who are interested in audio source separation techniques based on NMF, DNN and SCA. Front Matter ....Pages i-viii Single-Channel Audio Source Separation with NMF: Divergences, Constraints and Algorithms (Cédric Févotte, Emmanuel Vincent, Alexey Ozerov)....Pages 1-24 Separation of Known Sources Using Non-negative Spectrogram Factorisation (Tuomas Virtanen, Tom Barker)....Pages 25-48 Dynamic Non-negative Models for Audio Source Separation (Paris Smaragdis, Gautham Mysore, Nasser Mohammadiha)....Pages 49-71 An Introduction to Multichannel NMF for Audio Source Separation (Alexey Ozerov, Cédric Févotte, Emmanuel Vincent)....Pages 73-94 General Formulation of Multichannel Extensions of NMF Variants (Hirokazu Kameoka, Hiroshi Sawada, Takuya Higuchi)....Pages 95-124 Determined Blind Source Separation with Independent Low-Rank Matrix Analysis (Daichi Kitamura, Nobutaka Ono, Hiroshi Sawada, Hirokazu Kameoka, Hiroshi Saruwatari)....Pages 125-155 Deep Neural Network Based Multichannel Audio Source Separation (Aditya Arie Nugraha, Antoine Liutkus, Emmanuel Vincent)....Pages 157-185 Efficient Source Separation Using Bitwise Neural Networks (Minje Kim, Paris Smaragdis)....Pages 187-206 DNN Based Mask Estimation for Supervised Speech Separation (Jitong Chen, DeLiang Wang)....Pages 207-235 Informed Spatial Filtering Based on Constrained Independent Component Analysis (Hendrik Barfuss, Klaus Reindl, Walter Kellermann)....Pages 237-278 Recent Advances in Multichannel Source Separation and Denoising Based on Source Sparseness (Nobutaka Ito, Shoko Araki, Tomohiro Nakatani)....Pages 279-300 Multimicrophone MMSE-Based Speech Source Separation (Shmulik Markovich-Golan, Israel Cohen, Sharon Gannot)....Pages 301-331 Musical-Noise-Free Blind Speech Extraction Based on Higher-Order Statistics Analysis (Hiroshi Saruwatari, Ryoichi Miyazaki)....Pages 333-364 Audio-Visual Source Separation with Alternating Diffusion Maps (David Dov, Ronen Talmon, Israel Cohen)....Pages 365-382 Back Matter ....Pages 383-385