# PromptReverb: Multimodal Room Impulse Response Generation Through Latent Rectified Flow Matching

arXiv: https://arxiv.org/abs/2510.22439 · HTML: https://mlsanity.com/paper/2510.22439/

## 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 25 of its 38 references that are in the map.
- First posted on arXiv 25 Oct 2025.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [Rectified Flow: A Marginal Preserving Approach to Optimal Transport](https://mlsanity.com/paper/2209.14577/) (2022)
- [Pyroomacoustics: A Python package for audio room simulations and array processing algorithms](https://mlsanity.com/paper/1710.04196/) (2017)
- [WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling](https://mlsanity.com/paper/2408.16532/) (2024)
- [SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning](https://mlsanity.com/paper/2206.08312/) (2022)
- [FAST-RIR: Fast neural diffuse room impulse response generator](https://mlsanity.com/paper/2110.04057/) (2021)
- [Image2Reverb: Cross-Modal Reverb Impulse Response Synthesis](https://mlsanity.com/paper/2103.14201/) (2021)
- [MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes](https://mlsanity.com/paper/2205.09248/) (2022)
- [AV-RIR: Audio-Visual Room Impulse Response Estimation](https://mlsanity.com/paper/2312.00834/) (2023)
- [Language-Guided Joint Audio-Visual Editing via One-Shot Adaptation](https://mlsanity.com/paper/2410.07463/) (2024)
- [Hearing Anywhere in Any Environment](https://mlsanity.com/paper/2504.10746/) (2025)
- [Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond](https://mlsanity.com/paper/2505.04621/) (2025)
- [Deep Room Impulse Response Completion](https://mlsanity.com/paper/2402.00859/) (2024)
- [DiffusionRIR: Room Impulse Response Interpolation using Diffusion Models](https://mlsanity.com/paper/2504.20625/) (2025)
- [Room Impulse Response Generation Conditioned on Acoustic Parameters](https://mlsanity.com/paper/2507.12136/) (2025)
- [MEAN-RIR: Multi-Modal Environment-Aware Network for Robust Room Impulse Response Estimation](https://mlsanity.com/paper/2509.05205/) (2025)

## Abstract (arXiv)

Room impulse response (RIR) generation remains a critical challenge for creating immersive virtual acoustic environments. Current methods suffer from two fundamental limitations: the scarcity of full-band RIR datasets and the inability of existing models to generate acoustically accurate responses from diverse input modalities. We present PromptReverb, a two-stage generative framework that addresses these challenges. Our approach combines a variational autoencoder that upsamples band-limited RIRs to full-band quality (48 kHz), and a conditional diffusion transformer model based on rectified flow matching that generates RIRs from descriptions in natural language. Empirical evaluation demonstrates that PromptReverb produces RIRs with superior perceptual quality and acoustic accuracy compared to existing methods, achieving 8.8% mean RT60 error compared to -37% for widely used baselines and yielding more realistic room-acoustic parameters. Our method enables practical applications in virtual reality, architectural acoustics, and audio production where flexible, high-quality RIR synthesis is essential.