Physics-Informed Transfer Learning for Data-Driven Sound Source Reconstruction in Near-Field Acoustic Holography
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911057731125248 |
|---|---|
| author | Luan, Xinmeng Pezzoli, Mirco Antonacci, Fabio Sarti, Augusto |
| author_facet | Luan, Xinmeng Pezzoli, Mirco Antonacci, Fabio Sarti, Augusto |
| contents | We propose a transfer learning framework for sound source reconstruction in Near-field Acoustic Holography (NAH), which adapts a well-trained data-driven model from one type of sound source to another using a physics-informed procedure. The framework comprises two stages: (1) supervised pre-training of a complex-valued convolutional neural network (CV-CNN) on a large dataset, and (2) purely physics-informed fine-tuning on a single data sample based on the Kirchhoff-Helmholtz integral. This method follows the principles of transfer learning by enabling generalization across different datasets through physics-informed adaptation. The effectiveness of the approach is validated by transferring a pre-trained model from a rectangular plate dataset to a violin top plate dataset, where it shows improved reconstruction accuracy compared to the pre-trained model and delivers performance comparable to that of Compressive-Equivalent Source Method (C-ESM). Furthermore, for successful modes, the fine-tuned model outperforms both the pre-trained model and C-ESM in accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_11070 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Physics-Informed Transfer Learning for Data-Driven Sound Source Reconstruction in Near-Field Acoustic Holography Luan, Xinmeng Pezzoli, Mirco Antonacci, Fabio Sarti, Augusto Audio and Speech Processing Sound We propose a transfer learning framework for sound source reconstruction in Near-field Acoustic Holography (NAH), which adapts a well-trained data-driven model from one type of sound source to another using a physics-informed procedure. The framework comprises two stages: (1) supervised pre-training of a complex-valued convolutional neural network (CV-CNN) on a large dataset, and (2) purely physics-informed fine-tuning on a single data sample based on the Kirchhoff-Helmholtz integral. This method follows the principles of transfer learning by enabling generalization across different datasets through physics-informed adaptation. The effectiveness of the approach is validated by transferring a pre-trained model from a rectangular plate dataset to a violin top plate dataset, where it shows improved reconstruction accuracy compared to the pre-trained model and delivers performance comparable to that of Compressive-Equivalent Source Method (C-ESM). Furthermore, for successful modes, the fine-tuned model outperforms both the pre-trained model and C-ESM in accuracy. |
| title | Physics-Informed Transfer Learning for Data-Driven Sound Source Reconstruction in Near-Field Acoustic Holography |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2507.11070 |