arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2606.06962eess.AS
收藏

FSC-Net:融合快速傅里叶卷积与渐进学习的语音带宽扩展

FSC-Net: Integrating Fast Fourier Convolutions and Progressive Learning for Speech Bandwidth Extension

Nanjing University(南京大学);Horizon Robotics(地平线机器人)

Xinan Chen, Xiaobin Rong, Qinwen Hu, Kai Chen, Jing Lu

AI总结:

提出FSC-Net,通过集成快速傅里叶卷积和频率渐进学习,高效建模跨频段谐波依赖,实现窄带到宽带语音的高保真重建,在VCTK 4kHz-48kHz任务上以1.54M参数取得领先的LSD和PESQ分数。

摘要:

语音带宽扩展(BWE)旨在从窄带输入重建高保真宽带音频。尽管近期方法取得了显著进展,但它们通常难以重建真实的高频相位和谐波结构,导致感知伪影。本文提出FSC-Net(全频谱上下文网络),一种参数高效的架构,旨在显式建模跨频段谐波依赖。通过将快速傅里叶卷积(FFCs)集成到复频谱映射框架中,FSC-Net将其感受野扩展到整个频谱,有效捕获长程频率交互。为解决高频生成的不适定性,我们新颖的频率渐进学习课程引导网络从粗到细地重建频谱细节。在VCTK和未见过的EARS数据集上的实验结果表明,FSC-Net提供了持续强劲的重建质量和泛化能力,尤其在具有挑战性的VCTK 4 kHz至48 kHz任务中。与规模更大的基线相比,我们的模型在保持高度紧凑的参数规模(1.54 M)的同时,取得了领先的LSD和PESQ分数。

英文摘要:

Speech bandwidth extension (BWE) aims to reconstruct high-fidelity wideband audio from narrowband inputs. While recent approaches have made significant progress, they often struggle to reconstruct realistic high-frequency phase and harmonic structures, leading to perceptual artifacts. In this paper, we propose FSC-Net (Full-Spectrum Context Network), a parameter-efficient architecture designed to explicitly model cross-band harmonic dependencies. By integrating Fast Fourier Convolutions (FFCs) into a complex spectral mapping framework, FSC-Net expands its receptive field to the entire spectrum, capturing long-range frequency interactions effectively. To address the ill-posed nature of high-frequency generation, our novel frequency-progressive learning curriculum guides the network to reconstruct spectral details from coarse to fine. Experimental results on the VCTK and unseen EARS datasets demonstrate that FSC-Net delivers consistently strong reconstruction quality and generalization, particularly in the challenging VCTK 4 kHz-to-48 kHz task. Compared to scaled-up baselines, our model attains leading LSD and PESQ scores while maintaining a highly compact parameter footprint (1.54 M).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑