Surrogate Source Model Learning For Determined Source Separation

Abstract

We propose to learn surrogate functions of universal speech priors for determined blind speech separation. Deep speech priors are highly desirable due to their high modelling power, but are not compatible with state-of-the-art independent vector analysis based on majorization-minimization (AuxIVA), since deriving the required surrogate function is not easy, nor always possible. Instead, we do away with exact majorization and directly approximate the surrogate. Taking advantage of iterative source steering (ISS) updates, we back propagate the permutation invariant separation loss through multiple iterations of AuxIVA. ISS lends itself well to this task due to its lower complexity and lack of matrix inversion. Experiments show large improvements in terms of scale invariant signal-to-distortion (SDR) ratio and word error rate compared to baseline methods. Training is done on two speakers mixtures and we experiment with two losses, SDR and coherence. We find that the learnt approximate sur

Stats

• citations18
• S2 citations—
• github stars0
• HF likes0
• heat score9.59
• arxiv keyscheibler2020surrogate

Related papers

• A Comparison And Combination Of Unsupervised Blind Source Separation Techniques (2021)0.00
• Determined Blind Source Separation Via Modeling Adjacent Frequency Band Correlations In Speech Signals (2025)0.00
• Independence-based Joint Dereverberation And Separation With Neural Source Model (2021)4.52
• Multichannel Blind Speech Source Separation With A Disjoint Constraint Source Model (2024)0.00
• Unsupervised Music Source Separation Using Differentiable Parametric Source Models (2022)10.97
• Data-driven Source Separation Based On Simplex Analysis (2018)0.00
• Amicable Examples For Informed Source Separation (2021)0.00
• Separate And Diffuse: Using A Pretrained Diffusion Model For Improving Source Separation (2023)0.00