UnDiff: Unsupervised Voice Restoration with Unconditional Diffusion Model
This work addresses speech processing challenges for applications in audio restoration and synthesis, but it is incremental as it builds on existing diffusion model techniques with task-specific adaptations.
The paper tackles the problem of solving various speech inverse tasks by introducing UnDiff, an unconditional diffusion model for speech waveform generation that can be adapted to tasks like degradation inversion, neural vocoding, and source separation, achieving performance comparable to baselines in bandwidth extension, declipping, vocoding, and speech source separation.
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.