FiPA-SR -- FiLM-Conditioned Perceptually Informed Audio Super-Resolution
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916062454349824 |
|---|---|
| author | Abreu, Wallace Biscainho, Luiz W. P. |
| author_facet | Abreu, Wallace Biscainho, Luiz W. P. |
| contents | Audio bandwidth extension aims to reconstruct missing high-frequency content from bandlimited signals. This paper proposes FiPA-SR, a GAN-based perceptual architecture capable of handling different input bandwidths within a single model. Building upon the previous $\textrm{AEROMamba}_\textrm{P}$ framework, the proposed model incorporates FiLM layers to adapt the reconstruction process according to the respective bandwidth. Experiments on the MUSDB dataset show that FiPA-SR outperforms the state-of-the-art AudioSR model across 8, 20, and 32 kHz input sampling rates. Moreover, the proposed architecture uses approximately 3$\times$ less GPU memory and performs inference more than 60$\times$ faster than the diffusion-based baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30594 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FiPA-SR -- FiLM-Conditioned Perceptually Informed Audio Super-Resolution Abreu, Wallace Biscainho, Luiz W. P. Audio and Speech Processing Audio bandwidth extension aims to reconstruct missing high-frequency content from bandlimited signals. This paper proposes FiPA-SR, a GAN-based perceptual architecture capable of handling different input bandwidths within a single model. Building upon the previous $\textrm{AEROMamba}_\textrm{P}$ framework, the proposed model incorporates FiLM layers to adapt the reconstruction process according to the respective bandwidth. Experiments on the MUSDB dataset show that FiPA-SR outperforms the state-of-the-art AudioSR model across 8, 20, and 32 kHz input sampling rates. Moreover, the proposed architecture uses approximately 3$\times$ less GPU memory and performs inference more than 60$\times$ faster than the diffusion-based baseline. |
| title | FiPA-SR -- FiLM-Conditioned Perceptually Informed Audio Super-Resolution |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2605.30594 |