Undiff: Unsupervised Voice Restoration With Unconditional Diffusion Model

Abstract

This paper introduces UnDiff, a diffusion probabilistic model capable of solving various speech inverse tasks. Being once trained for speech waveform generation in an unconditional manner, it can be adapted to different tasks including degradation inversion, neural vocoding, and source separation. In this paper, we, first, tackle the challenging problem of unconditional waveform generation by comparing different neural architectures and preconditioning domains. After that, we demonstrate how the trained unconditional diffusion could be adapted to different tasks of speech processing by the means of recent developments in post-training conditioning of diffusion models. Finally, we demonstrate the performance of the proposed technique on the tasks of bandwidth extension, declipping, vocoding, and speech source separation and compare it to the baselines. The codes are publicly available.

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keyiashchenko2023undiff

Related papers

• Diffar: Denoising Diffusion Autoregressive Model For Raw Speech Waveform Generation (2023)0.00
• Cold Diffusion For Speech Enhancement (2022)11.85
• Diffwave: A Versatile Diffusion Model For Audio Synthesis (2020)0.00
• Fastdiff: A Fast Conditional Diffusion Model For High-quality Speech Synthesis (2022)14.35
• Extract And Diffuse: Latent Integration For Improved Diffusion-based Speech And Vocal Enhancement (2024)0.00
• Diffusion-based Signal Refiner For Speech Enhancement And Separation (2023)2.26
• Solving Audio Inverse Problems With A Diffusion Model (2022)0.00
• Infergrad: Improving Diffusion Models For Vocoder By Considering Inference In Training (2022)9.41