用单模型实现多带宽音频超分辨率，性能超越现有方法。
FiPA-SR -- FiLM-Conditioned Perceptually Informed Audio Super-Resolution
- 引入FiLM层按输入带宽动态调整重建过程。
- 在8/20/32 kHz下均优于AudioSR，且推理速度提升60倍。
- 仅需约1/3的显存，适合实时音频增强场景。
音频带宽扩展旨在从受限带宽信号中重建缺失的高频内容。本文提出FiPA-SR，一种基于GAN的感知架构，可在单一模型中处理不同输入带宽。在AEROMamba_P框架基础上，引入FiLM层以根据输入带宽自适应调整重建过程。在MUSDB数据集上的实验表明，FiPA-SR在8、20和32 kHz输入采样率下均优于当前最优的AudioSR模型。此外，该架构仅需约3倍更少的GPU内存，且推理速度比基于扩散模型的基线快60倍以上。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。