Subband Splitting: Simple, Efficient and Effective Technique for Solving Block Permutation Problem in Determined Blind Source Separation

2024-09-14

arXiv.org

AI Summary

To address the permutation ambiguity problem inherent in frequency-domain blind source separation (BSS) methods—specifically Independent Vector Analysis (IVA) and Independent Low-Rank Matrix Analysis (ILRMA)—this paper proposes a Subband Splitting (SS) framework. The spectrogram is partitioned into overlapping subbands; BSS is applied sequentially to each subband, with the separation result from the preceding subband used to initialize the current one, thereby achieving inter-subband permutation alignment. This work is the first to jointly integrate subband decomposition with cross-band initialization, enabling near-ideal permutation performance without supervision or auxiliary modeling. Based on this framework, two novel algorithms—SS-IVA and SS-ILRMA—are developed. They achieve substantial improvements in separation quality and convergence speed with negligible additional computational cost. Experiments demonstrate that SS-ILRMA matches the performance of frequency-domain ICA equipped with an ideal permutation solver, while converging significantly faster than conventional IVA and ILRMA.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Solving the permutation problem is essential for determined blind source separation (BSS). Existing methods, such as independent vector analysis (IVA) and independent low-rank matrix analysis (ILRMA), tackle the permutation problem by modeling the co-occurrence of the frequency components of source signals. One of the remaining challenges in these methods is the block permutation problem, which may cause severe performance degradation. In this paper, we propose a simple and effective technique for solving the block permutation problem. The proposed technique splits the entire frequency bands into several overlapping subbands and sequentially applies BSS methods (e.g., IVA, ILRMA, or any other method) to each subband. Since the splitting reduces the size of the problem, the BSS methods can effectively work in each subband. Then, the permutations among the subbands are aligned by using the separation result in one subband as the initial values for the other subbands. Additionally, we propose SS-IVA and SS-ILRMA by combining subband splitting with IVA and ILRMA. Experimental results demonstrated that our technique remarkably improves the separation performance without increasing computational cost. In particular, our SS-ILRMA archived the separation performance comparable to the oracle method (frequency-domain independent component analysis with the ideal permutation solver). Moreover, SS-ILRMA converged faster than conventional IVA and ILRMA.

Problem

• Blind Source Separation
• Block Permutation Problem
• Deterministic BSS

Innovation

• Subband Splitting
• Deterministic Blind Source Separation
• Enhanced Separation Performance