提出 LipsAM，让语音处理模型更稳定可靠。
LipsAM: Lipschitz-Continuous Amplitude Modifier for Audio Signal Processing and its Application to Plug-and-Play Dereverberation
- 设计满足李普希茨连续性的语音幅度调节模块。
- 在去混响任务中验证了模型稳定性提升。
- 适合关注模型可靠性的语音处理研究者。
深度神经网络（DNN）的鲁棒性可通过其李普希茨连续性进行认证，构建李普希茨连续的DNN是当前活跃的研究方向。然而，由于与现有成果兼容性差，音频处理领域的DNN尚未成为重点。本文聚焦于处理音频信号的常用架构——幅度调节器（AM），提出了其李普希茨连续变体，称为LipsAM。我们证明了AM具备李普希茨连续性的充分条件，并给出了两种LipsAM架构作为实例。将所提架构应用于即插即用的语音去混响算法，在数值实验中验证了其增强的稳定性。
原文摘要 · Abstract (English)
The robustness of deep neural networks (DNNs) can be certified through their Lipschitz continuity, which has made the construction of Lipschitz-continuous DNNs an active research field. However, DNNs for audio processing have not been a major focus due to their poor compatibility with existing results. In this paper, we consider the amplitude modifier (AM), a popular architecture for handling audio signals, and propose its Lipschitz-continuous variants, which we refer to as LipsAM. We prove a sufficient condition for an AM to be Lipschitz continuous and propose two architectures as examples of LipsAM. The proposed architectures were applied to a Plug-and-Play algorithm for speech dereverberation, and their improved stability is demonstrated through numerical experiments.
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。