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 2211.02527eess.AScs.SD
收藏

用于语音增强的 Cold Diffusion

Cold Diffusion for Speech Enhancement

Mitsubishi Electric Research Laboratories (MERL)(三菱电机研究实验室);Georgia Institute of Technology(佐治亚理工学院)

Hao Yen, François G. Germain, Gordon Wichern, Jonathan Le Roux

AI总结:

本研究探索利用 cold diffusion 从含噪信号中恢复干净语音信号,提出改进的训练算法和目标函数以提升泛化能力,并在 VoiceBank-DEMAND 数据集上验证了其优于判别式模型和基于 diffusion 的增强模型的性能。

摘要:

Diffusion models 最近在困难增强任务中展现出令人鼓舞的结果,例如自然图像和音频信号的条件与无条件恢复。在本研究中,我们探索利用最近提出的一种先进迭代 diffusion model,即 cold diffusion,从含噪信号中恢复干净语音信号的可能性。从 cold diffusion 采样的独特数学特性可用于从任意退化中恢复高质量样本。基于这些特性,我们提出了一种改进的训练算法和目标函数,以帮助模型在采样过程中更好地泛化。我们通过研究两种模型架构验证了所提出的框架。在基准语音增强数据集 VoiceBank-DEMAND 上的实验结果表明,与代表性的判别式模型和基于 diffusion 的增强模型相比,所提出的方法具有很强的性能。

英文摘要:

Diffusion models have recently shown promising results for difficult enhancement tasks such as the conditional and unconditional restoration of natural images and audio signals. In this work, we explore the possibility of leveraging a recently proposed advanced iterative diffusion model, namely cold diffusion, to recover clean speech signals from noisy signals. The unique mathematical properties of the sampling process from cold diffusion could be utilized to restore high-quality samples from arbitrary degradations. Based on these properties, we propose an improved training algorithm and objective to help the model generalize better during the sampling process. We verify our proposed framework by investigating two model architectures. Experimental results on benchmark speech enhancement dataset VoiceBank-DEMAND demonstrate the strong performance of the proposed approach compared to representative discriminative models and diffusion-based enhancement models.

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。

↑