# Generative Learning for Ambisonic Upscaling

arXiv: https://arxiv.org/abs/2609.23479 · HTML: https://mlsanity.com/paper/2609.23479/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 24 of its 54 references that are in the map.
- First posted on arXiv 20 Sep 2026.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 24 of 24)

- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022)
- [A Survey on Diffusion Models for Inverse Problems](https://mlsanity.com/paper/2410.00083/) (2024)
- [Pyroomacoustics: A Python package for audio room simulations and array processing algorithms](https://mlsanity.com/paper/1710.04196/) (2017)
- [Simple ReFlow: Improved Techniques for Fast Flow Models](https://mlsanity.com/paper/2410.07815/) (2024)
- [Diffusion Models for Audio Restoration](https://mlsanity.com/paper/2402.09821/) (2024)
- [Discriminative and Generative Learning for Linear Estimation of Random Signals [Lecture Notes]](https://mlsanity.com/paper/2206.04432/) (2022)
- [Deep Unfolding: Recent Developments, Theory, and Design Guidelines](https://mlsanity.com/paper/2512.03768/) (2025)
- [Diff-SAGe: End-to-End Spatial Audio Generation Using Diffusion Models](https://mlsanity.com/paper/2410.11299/) (2024)
- [EDSep: An Effective Diffusion-Based Method for Speech Source Separation](https://mlsanity.com/paper/2501.15965/) (2025)
- [Ambisonics Encoding For Arbitrary Microphone Arrays Incorporating Residual Channels For Binaural Reproduction](https://mlsanity.com/paper/2402.17362/) (2024)
- [A Physics-Informed Neural Network-Based Approach for the Spatial Upsampling of Spherical Microphone Arrays](https://mlsanity.com/paper/2407.18732/) (2024)
- [Gen-A: Generalizing Ambisonics Neural Encoding to Unseen Microphone Arrays](https://mlsanity.com/paper/2501.08047/) (2025)
- [Ambisonics Super-Resolution Using A Waveform-Domain Neural Network](https://mlsanity.com/paper/2508.00240/) (2025)
- [DiffAU: Diffusion-Based Ambisonics Upscaling](https://mlsanity.com/paper/2510.00180/) (2025)
- [Ambisonizer: Neural Upmixing as Spherical Harmonics Generation](https://mlsanity.com/paper/2405.13428/) (2024)
- [HARP: A Large-Scale Higher-Order Ambisonic Room Impulse Response Dataset](https://mlsanity.com/paper/2411.14207/) (2024)
- [AI-Aided Annealed Langevin Dynamics for Rapid Optimization of Programmable Channels](https://mlsanity.com/paper/2510.18978/) (2025)
- [ImmersiveFlow: Stereo-to-7.1.4 spatial audio generation with flow matching](https://mlsanity.com/paper/2601.12950/) (2026)
- [SIRUP: A diffusion-based virtual upmixer of steering vectors for highly-directive spatialization with first-order ambisonics](https://mlsanity.com/paper/2602.17732/) (2026)

## Abstract (arXiv)

Ambisonics Upscaling (AU) aims to enhance the spatial resolution of sound fields by estimating high-order Ambisonics (HOA) components from low-order observations. While deep learning and model-based strategies have been considered for AU, both approaches exhibit significant performance degradation in realistic scenarios, where reverberant sound fields violate the directional sparsity inherent to discriminative mappings. In this work, we address AU as a generative task rather than a deterministic reconstruction, expanding generative modeling to specifically target the recovery of spatial information in reverberant speech. We investigate two dominant continuous-time generative paradigms, adapting both Score-based Generative Model and Flow Matching to these complex acoustic settings. We provide an extensive numerical study comparing our methods against state-of-the-art baselines in various acoustic scenarios. Additionally, we conduct subjective listening tests to evaluate the perceived quality and spatial accuracy of the proposed generative framework across various reverberant scenarios. The studies reveal that Flow Matching consistently outperforms both its discriminative counterparts and Diffusion-based paradigms in all reverberant settings.