On Ambisonic Source Separation With Spatially Informed Non-negative Tensor Factorization

Abstract

This article presents a Non-negative Tensor Factorization based method for sound source separation from Ambisonic microphone signals. The proposed method enables the use of prior knowledge about the Directions-of-Arrival (DOAs) of the sources, incorporated through a constraint on the Spatial Covariance Matrix (SCM) within a Maximum a Posteriori (MAP) framework. Specifically, this article presents a detailed derivation of four algorithms that are based on two types of cost functions, namely the squared Euclidean distance and the Itakura-Saito divergence, which are then combined with two prior probability distributions on the SCM, that is the Wishart and the Inverse Wishart. The experimental evaluation of the baseline Maximum Likelihood (ML) and the proposed MAP methods is primarily based on first-order Ambisonic recordings, using four different source signal datasets, three with musical pieces and one containing speech utterances. We consider under-determined, determined, as well as ove

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyguzik2025on

Related papers

• Nonnegative Tensor Factorization With Frequency Modulation Cues For Blind Audio Source Separation (2016)0.00
• End-to-end Non-negative Autoencoders For Sound Source Separation (2019)2.26
• Complex NMF Under Phase Constraints Based On Signal Modeling: Application To Audio Source Separation (2016)7.50
• Spatial Loss For Unsupervised Multi-channel Source Separation (2022)7.16
• Generalized Multichannel Variational Autoencoder For Underdetermined Source Separation (2018)7.81
• Deep Bayesian Unsupervised Source Separation Based On A Complex Gaussian Mixture Model (2019)6.34
• Determined Multichannel Blind Source Separation With Clustered Source Model (2024)0.00
• Locate And Beamform: Two-dimensional Locating All-neural Beamformer For Multi-channel Speech Separation (2023)3.58