# SIRUP: A diffusion-based virtual upmixer of steering vectors for highly-directive spatialization with first-order ambisonics

arXiv: https://arxiv.org/abs/2602.17732 · HTML: https://mlsanity.com/paper/2602.17732/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Placed in

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

## Builds on (most cited first, 10 of 10)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Fast Timing-Conditioned Latent Audio Diffusion](https://mlsanity.com/paper/2402.04825/) (2024)
- [Pyroomacoustics: A Python package for audio room simulations and array processing algorithms](https://mlsanity.com/paper/1710.04196/) (2017)
- [Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks](https://mlsanity.com/paper/1807.00129/) (2018)
- [AudioSR: Versatile Audio Super-resolution at Scale](https://mlsanity.com/paper/2309.07314/) (2023)
- [Differentiable Tracking-Based Training of Deep Learning Sound Source Localizers](https://mlsanity.com/paper/2111.00030/) (2021)
- [Steered Response Power for Sound Source Localization: A Tutorial Review](https://mlsanity.com/paper/2405.02991/) (2024)
- [SLAM-based Joint Calibration of Multiple Asynchronous Microphone Arrays and Sound Source Localization](https://mlsanity.com/paper/2405.19813/) (2024)
- [A first-order DirAC-based parametric Ambisonic coder for immersive communications](https://mlsanity.com/paper/2503.23586/) (2025)

## Built on by (most cited first, 1 of 1)

- [Generative Learning for Ambisonic Upscaling](https://mlsanity.com/paper/2609.23479/) (2026)

## Abstract (arXiv)

This paper presents virtual upmixing of steering vectors captured by a fewer-channel spherical microphone array. This challenge has conventionally been addressed by recovering the directions and signals of sound sources from first-order ambisonics (FOA) data, and then rendering the higher-order ambisonics (HOA) data using a physics-based acoustic simulator. This approach, however, struggles to handle the mutual dependency between the spatial directivity of source estimation and the spatial resolution of FOA ambisonics data. Our method, named SIRUP, employs a latent diffusion model architecture. Specifically, a variational autoencoder (VAE) is used to learn a compact encoding of the HOA data in a latent space and a diffusion model is then trained to generate the HOA embeddings, conditioned by the FOA data. Experimental results showed that SIRUP achieved a significant improvement compared to FOA systems for steering vector upmixing, source localization, and speech denoising.