使用基于扩散的随机再生模型进行风噪降低
Wind Noise Reduction with a Diffusion-based Stochastic Regeneration Model
AI总结:
本文提出结合预测与生成建模的基于扩散的随机再生模型进行单通道风噪降低,引入非加性语音模型处理非线性形变与削波,在模拟与真实数据上优于现有方法且泛化良好。
摘要:
本文提出了一种单通道风噪降低方法,使用我们先前提出的基于扩散的随机再生模型,结合了预测性和生成性建模。我们引入了一种非加性噪声中的语音模型,以解释由风流引起的膜的非线性变形以及可能的削波。我们在一个使用模拟和真实录制风噪的数据集上展示了,我们的随机再生模型优于其他基于神经网络的风噪降低方法以及纯预测性和生成性模型。我们进一步展示了所提方法具有良好的泛化能力,通过在一个未见过的真实录制风噪数据集上进行测试。所提方法的音频样本、数据生成脚本和代码可在网上找到。
英文摘要:
In this paper we present a method for single-channel wind noise reduction using our previously proposed diffusion-based stochastic regeneration model combining predictive and generative modelling. We introduce a non-additive speech in noise model to account for the non-linear deformation of the membrane caused by the wind flow and possible clipping. We show that our stochastic regeneration model outperforms other neural-network-based wind noise reduction methods as well as purely predictive and generative models, on a dataset using simulated and real-recorded wind noise. We further show that the proposed method generalizes well by testing on an unseen dataset with real-recorded wind noise. Audio samples, data generation scripts and code for the proposed methods can be found online (https://uhh.de/inf-sp-storm-wind).
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。