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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lin, Jackie, Su, Jiaqi, Anand, Nishit, Jin, Zeyu, Kim, Minje, Smaragdis, Paris
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914318249885696
author Lin, Jackie
Su, Jiaqi
Anand, Nishit
Jin, Zeyu
Kim, Minje
Smaragdis, Paris
author_facet Lin, Jackie
Su, Jiaqi
Anand, Nishit
Jin, Zeyu
Kim, Minje
Smaragdis, Paris
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_09233
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Gencho: Room Impulse Response Generation from Reverberant Speech and Text via Diffusion Transformers
Lin, Jackie
Su, Jiaqi
Anand, Nishit
Jin, Zeyu
Kim, Minje
Smaragdis, Paris
Sound
Audio and Speech Processing
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.
title Gencho: Room Impulse Response Generation from Reverberant Speech and Text via Diffusion Transformers
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2602.09233