# Iterative Audio Separation with Mixture Consistency via MIMO Model Extension

arXiv: https://arxiv.org/abs/2609.07226 · HTML: https://mlsanity.com/paper/2609.07226/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 35 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 30 of 32)

- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022)
- [Hybrid Spectrogram and Waveform Source Separation](https://mlsanity.com/paper/2111.03600/) (2021)
- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [Multi-Source Diffusion Models for Simultaneous Music Generation and Separation](https://mlsanity.com/paper/2302.02257/) (2023)
- [SingSong: Generating musical accompaniments from singing](https://mlsanity.com/paper/2301.12662/) (2023)
- [A Study on Speech Enhancement Based on Diffusion Probabilistic Model](https://mlsanity.com/paper/2107.11876/) (2021)
- [The 2018 Signal Separation Evaluation Campaign](https://mlsanity.com/paper/1804.06267/) (2018)
- [Universal Sound Separation](https://mlsanity.com/paper/1905.03330/) (2019)
- [Diffusion-based Generative Speech Source Separation](https://mlsanity.com/paper/2210.17327/) (2022)
- [Moisesdb: A dataset for source separation beyond 4-stems](https://mlsanity.com/paper/2307.15913/) (2023)
- [Music Source Separation with Band-Split RoPE Transformer](https://mlsanity.com/paper/2309.02612/) (2023)
- [Differentiable Consistency Constraints for Improved Deep Speech Enhancement](https://mlsanity.com/paper/1811.08521/) (2018)
- [FlowSep: Language-Queried Sound Separation with Rectified Flow Matching](https://mlsanity.com/paper/2409.07614/) (2024)
- [FlowSE: Flow Matching-based Speech Enhancement](https://mlsanity.com/paper/2508.06840/) (2025)
- [WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration](https://mlsanity.com/paper/2210.01029/) (2022)
- [On loss functions and evaluation metrics for music source separation](https://mlsanity.com/paper/2202.07968/) (2022)
- [Mel-Band RoFormer for Music Source Separation](https://mlsanity.com/paper/2310.01809/) (2023)
- [MusicGen-Stem: Multi-stem music generation and edition through autoregressive modeling](https://mlsanity.com/paper/2501.01757/) (2025)
- [Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction](https://mlsanity.com/paper/1711.00048/) (2017)
- [End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction](https://mlsanity.com/paper/1804.10204/) (2018)
- [SCNet: Sparse Compression Network for Music Source Separation](https://mlsanity.com/paper/2401.13276/) (2024)
- [Adversarial Permutation Invariant Training for Universal Sound Separation](https://mlsanity.com/paper/2210.12108/) (2022)
- [Source Separation by Flow Matching](https://mlsanity.com/paper/2505.16119/) (2025)
- [Music Source Separation with Deep Equilibrium Models](https://mlsanity.com/paper/2110.06494/) (2021)
- [FastSAG: Towards Fast Non-Autoregressive Singing Accompaniment Generation](https://mlsanity.com/paper/2405.07682/) (2024)
- [A Two-Stage Band-Split Mamba-2 Network For Music Separation](https://mlsanity.com/paper/2409.06245/) (2024)
- [User-guided Generative Source Separation](https://mlsanity.com/paper/2507.01339/) (2025)
- [AnyAccomp: Generalizable Accompaniment Generation via Quantized Melodic Bottleneck](https://mlsanity.com/paper/2509.14052/) (2025)

## Abstract (arXiv)

This paper proposes a general framework for stable and effective iterative audio separation with mixture consistency by extending source separation models to a multi-input multi-output (MIMO) configuration. In the field of audio separation, mixture consistency is an essential property for many applications that require accurate phase and timbral information of target sources. While iterative approaches such as diffusion models achieve perceptually superior results in speech enhancement or user-guided target source separation tasks, most existing methods focus on single-step separation with a single-input single-output (SISO) or single-input multi-output (SIMO) configuration through architectural improvements, since mixture-consistent audio separation is generally regarded as a regression problem that admits a unique solution. By extending these architectures to a MIMO configuration, we introduce iterative prediction without compromising the architectural advantages or the characteristics of mixture consistency. We conduct a comprehensive ablation study of combining the framework with discriminators and extending it to a generative model. Experimental results demonstrate significant performance improvements when applying the proposed framework to state-of-the-art separation models.