Blind Source Separation and Independent Component Analysis : A Review

By Seungjin Choi. 2004

How researchers see this paper

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

1. Eliya Nachmani
2. Lior Wolf
3. Yossi Adi
4. Yi Luo
5. Nima Mesgarani
6. Zhuo Chen
7. Alexandre D'efossez
8. Wei-Ning Hsu

Citations in the corpus

• Voice Separation with an Unknown Number of Multiple Speakers (2020, methodology): “, 2018), where traditionally signal processing techniques were applied to the task (Choi et al., 2005).”
• Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation (2018, background): “Beyond ICA methods, several recent studies have investigated the feasibility of time-domain separation with deep learning [18], [19], [20].”
• Speaker-Independent Speech Separation With Deep Attractor Network (2017, methodology): “In statistical methods, the target speech signal is modeled with probability distributions such as complex Gaussian [9] or methods such as independent component analysis (ICA) [10], where the interference signal is assumed to be statistically independent from the target speech.”
• Robust artifactual independent component classification for BCI practitioners (2014, background): “Because a thorough analysis of the achievable separation performance is out of the scope of this paper, we refer the reader to [17, 23, 24] on the question of which ICA variants are”
• EEG artifact removal—state-of-the-art and guidelines (2015, methodology): “In fact, leading researchers in the field have been using ICA and improved variations for the last 15 years—for example Vigário [21, 44, 159, 160], Hÿvarinen [161, 162], Oja [21, 159, 161, 162], James [20, 39, 55, 108], Makeig [43, 52, 97, 102], Jung [43, 52, 97], Comon [41] and Cichocki [83, 163], ”
• Artifact Removal in Physiological Signals—Practices and Possibilities (2012, background): “[76], are: 1) the use of higher order statistics (HOS) including skewness and kurtosis; 2) second-order statistics (SOS) including”
• A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI (2023, unknown): “To overcome these problems, other time-domain approaches are proposed, including independent component analysis (ICA) [12], non-negative matrix factorization(NMF) [131].”
• A Block Coordinate Descent Method for Regularized Multiconvex Optimization with Applications to Nonnegative Tensor Factorization and Completion (2013, methodology): “Two classical approaches for BSS are principle component analysis (PCA) [62] and independent component analysis (ICA) [18].”