A robust and precise method for solving the permutation problem of frequency-domain blind source separation

By Hiroshi Sawada, R. Mukai, Shoko Araki, Shoji Makino. IEEE Transactions on Speech and Audio Processing, 2004

621 citations recorded by the source corpus.

Subfields: Computational Mechanics, Signal Processing

View Paper: https://www.semanticscholar.org/paper/baebe2189e960d9125621b385fa8eb81539e7348

How researchers see this paper

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

In Computational Mechanics

In Signal Processing

Citations in the corpus

Blind Source Separation and Independent Component Analysis: A Review (2005, methodology): “In order to exploit the advantages of the two methods, a method fixed the permutations at some frequency bins where the confidence of the DOA method was sufficiently high, and then decided the permutations for the remaining frequency bins by the envelopes of frequency spectra [129].”
Blind Source Separation and Independent Component Analysis : A Review (2004, methodology): “In order to exploit the advantages of the two methods, a method fixed the permutations at some frequency bins where the confidence of the DOA method was sufficiently high, and then decided the permutations for the remaining frequency bins by the envelopes of frequency spectra [129].”
Underdetermined Convolutive Blind Source Separation via Frequency Bin-Wise Clustering and Permutation Alignment (2011, methodology): “Amplitude envelopes are widely used [9], [10], [24], [25] to represent the activity of separated signals and thus for permutation alignment.”
Time-domain blind audio source separation using advanced ICA methods (2007, methodology): “In this fashion, the audio BSS can be performed via ICA either in frequency domain [5, 1, 11] or in time domain [14].”
A Consolidated Perspective on Multimicrophone Speech Enhancement and Source Separation (2017, positive): “In [47], the inter-frame model and the full-rank model are combined in a nested MVDR beamforming structure.”
Time-Domain Blind Separation of Audio Sources on the Basis of a Complete ICA Decomposition of an Observation Space (2011, neutral): “1 and 2.”
Stable and fast update rules for independent vector analysis based on auxiliary function technique (2011, background): “Index Terms— independent vector analysis, blind source separation, natural gradient, auxiliary function”
Blind Source Separation Exploiting Higher-Order Frequency Dependencies (2007, methodology): “separating matrix, source directions can be estimated and, therefore, permutations can be aligned [12]–[14].”
Cracking the cocktail party problem by multi-beam deep attractor network (2017, methodology): “Various beamforming, or more precisely spatial ﬁltering, methods were proposed by using, for example, Independent Component Analysis [16, 17].”
An Investigation into the Effectiveness of Enhancement in ASR Training and Test for Chime-5 Dinner Party Transcription (2019, background): “This has a major practical application, since frequency permutation solvers like [21] become obsolete.”
Determined Blind Source Separation Unifying Independent Vector Analysis and Nonnegative Matrix Factorization (2016, background): “IVA [16]–[18] is a multivariate extension of FDICA and can solve the permutation problem [12]–[14].”