Data Augmentation Using Neural Acoustic Fields With Retrieval-Augmented Pre-training
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909585915248640 |
|---|---|
| author | Ick, Christopher Wichern, Gordon Masuyama, Yoshiki Germain, François G. Roux, Jonathan Le |
| author_facet | Ick, Christopher Wichern, Gordon Masuyama, Yoshiki Germain, François G. Roux, Jonathan Le |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14409 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Data Augmentation Using Neural Acoustic Fields With Retrieval-Augmented Pre-training Ick, Christopher Wichern, Gordon Masuyama, Yoshiki Germain, François G. Roux, Jonathan Le Audio and Speech Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Sound 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. |
| title | Data Augmentation Using Neural Acoustic Fields With Retrieval-Augmented Pre-training |
| topic | Audio and Speech Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Sound |
| url | https://arxiv.org/abs/2504.14409 |