A Zero-Shot Physics-Informed Dictionary Learning Approach for Sound Field Reconstruction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912169192325120 |
|---|---|
| author | Damiano, Stefano Miotello, Federico Pezzoli, Mirco Bernardini, Alberto Antonacci, Fabio Sarti, Augusto van Waterschoot, Toon |
| author_facet | Damiano, Stefano Miotello, Federico Pezzoli, Mirco Bernardini, Alberto Antonacci, Fabio Sarti, Augusto van Waterschoot, Toon |
| contents | Sound field reconstruction aims to estimate pressure fields in areas lacking direct measurements. Existing techniques often rely on strong assumptions or face challenges related to data availability or the explicit modeling of physical properties. To bridge these gaps, this study introduces a zero-shot, physics-informed dictionary learning approach to perform sound field reconstruction. Our method relies only on a few sparse measurements to learn a dictionary, without the need for additional training data. Moreover, by enforcing the Helmholtz equation during the optimization process, the proposed approach ensures that the reconstructed sound field is represented as a linear combination of a few physically meaningful atoms. Evaluations on real-world data show that our approach achieves comparable performance to state-of-the-art dictionary learning techniques, with the advantage of requiring only a few observations of the sound field and no training on a dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18348 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Zero-Shot Physics-Informed Dictionary Learning Approach for Sound Field Reconstruction Damiano, Stefano Miotello, Federico Pezzoli, Mirco Bernardini, Alberto Antonacci, Fabio Sarti, Augusto van Waterschoot, Toon Audio and Speech Processing Signal Processing Sound field reconstruction aims to estimate pressure fields in areas lacking direct measurements. Existing techniques often rely on strong assumptions or face challenges related to data availability or the explicit modeling of physical properties. To bridge these gaps, this study introduces a zero-shot, physics-informed dictionary learning approach to perform sound field reconstruction. Our method relies only on a few sparse measurements to learn a dictionary, without the need for additional training data. Moreover, by enforcing the Helmholtz equation during the optimization process, the proposed approach ensures that the reconstructed sound field is represented as a linear combination of a few physically meaningful atoms. Evaluations on real-world data show that our approach achieves comparable performance to state-of-the-art dictionary learning techniques, with the advantage of requiring only a few observations of the sound field and no training on a dataset. |
| title | A Zero-Shot Physics-Informed Dictionary Learning Approach for Sound Field Reconstruction |
| topic | Audio and Speech Processing Signal Processing |
| url | https://arxiv.org/abs/2412.18348 |