arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.03065cs.SDcs.LGeess.AS
收藏

基于分数扩散的通用语音增强

Universal Speech Enhancement with Score-based Diffusion

Dolby Laboratories(杜比实验室);Universitat Pompeu Fabra(庞培法布拉大学)

Joan Serrà, Santiago Pascual, Jordi Pons, R. Oguz Araz, Davide Scaini

摘要:

从语音音频中去除背景噪声一直是相当大的努力的主题,特别是近年来由于虚拟通信和业余录音的兴起。然而,背景噪声并不是唯一会妨碍清晰度的令人不快的干扰:混响、削波、编解码器伪影、有问题的均衡、有限的带宽或不一致的响度同样令人不安且无处不在。在这项工作中,我们建议考虑语音增强的任务作为一个整体的努力,并提出了一个通用的语音增强系统,同时处理55个不同的失真。我们的方法包括一个生成模型,采用基于分数的扩散,以及一个多分辨率条件网络,执行增强与混合密度网络。我们表明,这种方法显着优于最先进的主观测试中进行的专家听众。我们还表明,尽管没有考虑任何特定的快速采样策略,但它仅用4-8个扩散步骤就实现了具有竞争力的客观分数。我们希望我们的方法和技术贡献鼓励研究人员和从业者采用通用的方法来增强语音,可能将其框定为生成任务。

英文摘要:

Removing background noise from speech audio has been the subject of considerable effort, especially in recent years due to the rise of virtual communication and amateur recordings. Yet background noise is not the only unpleasant disturbance that can prevent intelligibility: reverb, clipping, codec artifacts, problematic equalization, limited bandwidth, or inconsistent loudness are equally disturbing and ubiquitous. In this work, we propose to consider the task of speech enhancement as a holistic endeavor, and present a universal speech enhancement system that tackles 55 different distortions at the same time. Our approach consists of a generative model that employs score-based diffusion, together with a multi-resolution conditioning network that performs enhancement with mixture density networks. We show that this approach significantly outperforms the state of the art in a subjective test performed by expert listeners. We also show that it achieves competitive objective scores with just 4-8 diffusion steps, despite not considering any particular strategy for fast sampling. We hope that both our methodology and technical contributions encourage researchers and practitioners to adopt a universal approach to speech enhancement, possibly framing it as a generative task.

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。

↑