Data Augmentation Using Neural Acoustic Fields With Retrieval-Augmented Pre-training

Christopher Ick, Gordon Wichern, Yoshiki Masuyama, François G. Germain, Jonathan Le Roux
4/19/2025
eess.AScs.AIcs.CV

No confident code implementation found for this paper. 3 possible matches can be shown below.

Abstract

This report details MERL's system for room impulse response (RIR) estimation submitted to the Generative Data Augmentation Workshop at ICASSP 2025 for Augmenting RIR Data (Task 1) and Improving Speaker Distance Estimation (Task 2). We first pre-train a neural acoustic field conditioned by room geometry on an external large-scale dataset in which pairs of RIRs and the geometries are provided. The neural acoustic field is then adapted to each target room by using the enrollment data, where we leverage either the provided room geometries or geometries retrieved from the external dataset, depending on availability. Lastly, we predict the RIRs for each pair of source and receiver locations specified by Task 1, and use these RIRs to train the speaker distance estimation model in Task 2.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 3 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

FAST-RIR: Fast neural diffuse room impulse response generator

82% match1 repo1842021

RIR-SF: Room Impulse Response Based Spatial Feature for Target Speech Recognition in Multi-Channel Multi-Speaker Scenarios

82% match2023

Explicit Context-Driven Neural Acoustic Modeling for High-Fidelity RIR Generation

82% match2025

Direction-Aware Neural Acoustic Fields for Few-Shot Interpolation of Ambisonic Impulse Responses

81% match2025

Bayesian inference and neural estimation of acoustic wave propagation

80% match2023

Reconstruction of Sound Field through Diffusion Models

80% match2023

Cite this paper

@article{ick2025data,
  title  = {Data Augmentation Using Neural Acoustic Fields With Retrieval-Augmented Pre-training},
  author = {Christopher Ick and Gordon Wichern and Yoshiki Masuyama and François G. Germain and Jonathan Le Roux},
  year   = {2025},
  eprint = {2504.14409},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2504.14409v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2504.14409.svg)](https://codeofpaper.com/paper/2504.14409)

Discussion