Saved in:
Bibliographic Details
Main Authors: Kim, Kirak, Kim, Sungyoung
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.09708
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914560410124288
author Kim, Kirak
Kim, Sungyoung
author_facet Kim, Kirak
Kim, Sungyoung
contents Room Impulse Responses (RIRs) enable realistic acoustic simulation, with applications ranging from multimedia production to speech data augmentation. However, acquiring high-quality real-world RIRs is labor-intensive, and data scarcity remains a challenge for data-driven RIR generation approaches. In this paper, we propose a novel approach to RIR generation by adapting a pre-trained text-to-audio model, demonstrating for the first time that large-scale generative audio priors can be effectively leveraged for the task. To address the lack of text-RIR paired data, we utilize a labeling pipeline leveraging vision-language models to extract acoustic descriptions from existing image-RIR datasets. We introduce an in-context learning strategy to accommodate free-form user prompts during inference. Evaluations including subjective listening test demonstrate that our model generates plausible RIRs. Audio examples are available on our demo website.
format Preprint
id arxiv_https___arxiv_org_abs_2603_09708
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Adapting a Text-to-Audio Model for Room Impulse Response Generation
Kim, Kirak
Kim, Sungyoung
Audio and Speech Processing
Room Impulse Responses (RIRs) enable realistic acoustic simulation, with applications ranging from multimedia production to speech data augmentation. However, acquiring high-quality real-world RIRs is labor-intensive, and data scarcity remains a challenge for data-driven RIR generation approaches. In this paper, we propose a novel approach to RIR generation by adapting a pre-trained text-to-audio model, demonstrating for the first time that large-scale generative audio priors can be effectively leveraged for the task. To address the lack of text-RIR paired data, we utilize a labeling pipeline leveraging vision-language models to extract acoustic descriptions from existing image-RIR datasets. We introduce an in-context learning strategy to accommodate free-form user prompts during inference. Evaluations including subjective listening test demonstrate that our model generates plausible RIRs. Audio examples are available on our demo website.
title Adapting a Text-to-Audio Model for Room Impulse Response Generation
topic Audio and Speech Processing
url https://arxiv.org/abs/2603.09708