HyperSound: Generating Implicit Neural Representations of Audio Signals with Hypernetworks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913207935827968 |
|---|---|
| author | Szatkowski, Filip Piczak, Karol J. Spurek, Przemysław Tabor, Jacek Trzciński, Tomasz |
| author_facet | Szatkowski, Filip Piczak, Karol J. Spurek, Przemysław Tabor, Jacek Trzciński, Tomasz |
| contents | Implicit neural representations (INRs) are a rapidly growing research field, which provides alternative ways to represent multimedia signals. Recent applications of INRs include image super-resolution, compression of high-dimensional signals, or 3D rendering. However, these solutions usually focus on visual data, and adapting them to the audio domain is not trivial. Moreover, it requires a separately trained model for every data sample. To address this limitation, we propose HyperSound, a meta-learning method leveraging hypernetworks to produce INRs for audio signals unseen at training time. We show that our approach can reconstruct sound waves with quality comparable to other state-of-the-art models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2211_01839 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | HyperSound: Generating Implicit Neural Representations of Audio Signals with Hypernetworks Szatkowski, Filip Piczak, Karol J. Spurek, Przemysław Tabor, Jacek Trzciński, Tomasz Sound Artificial Intelligence Machine Learning Neural and Evolutionary Computing Audio and Speech Processing Implicit neural representations (INRs) are a rapidly growing research field, which provides alternative ways to represent multimedia signals. Recent applications of INRs include image super-resolution, compression of high-dimensional signals, or 3D rendering. However, these solutions usually focus on visual data, and adapting them to the audio domain is not trivial. Moreover, it requires a separately trained model for every data sample. To address this limitation, we propose HyperSound, a meta-learning method leveraging hypernetworks to produce INRs for audio signals unseen at training time. We show that our approach can reconstruct sound waves with quality comparable to other state-of-the-art models. |
| title | HyperSound: Generating Implicit Neural Representations of Audio Signals with Hypernetworks |
| topic | Sound Artificial Intelligence Machine Learning Neural and Evolutionary Computing Audio and Speech Processing |
| url | https://arxiv.org/abs/2211.01839 |