Gencho: Room Impulse Response Generation from Reverberant Speech and Text via Diffusion Transformers

TL;DR

Gencho is a novel diffusion-transformer model that generates diverse, realistic room impulse responses from reverberant speech and text, improving flexibility and performance in acoustic simulation tasks.

Contribution

It introduces a structure-aware encoder and diffusion decoder for complex spectrogram RIR generation, enabling controllable and high-quality acoustic modeling.

Findings

Richer RIRs than non-generative baselines

Strong performance on standard RIR metrics

Effective text-conditioned RIR generation

Abstract

Blind room impulse response (RIR) estimation is a core task for capturing and transferring acoustic properties; yet existing methods often suffer from limited modeling capability and degraded performance under unseen conditions. Moreover, emerging generative audio applications call for more flexible impulse response generation methods. We propose Gencho, a diffusion-transformer-based model that predicts complex spectrogram RIRs from reverberant speech. A structure-aware encoder leverages isolation between early and late reflections to encode the input audio into a robust representation for conditioning, while the diffusion decoder generates diverse and perceptually realistic impulse responses from it. Gencho integrates modularly with standard speech processing pipelines for acoustic matching. Results show richer generated RIRs than non-generative baselines while maintaining strong performance in standard RIR metrics. We further demonstrate its application to text-conditioned RIR generation, highlighting Gencho's versatility for controllable acoustic simulation and generative audio tasks.