Deep Audio Prior
Deep convolutional neural networks are known to specialize in distilling compact and robust prior from a large amount of data. We are interested in applying deep networks in the absence of training dataset. In this paper, we introduce deep audio prior (DAP) which leverages the structure of a network and the temporal information in a single audio file. Specifically, we demonstrate that a randomly-initialized neural network can be used with carefully designed audio prior to tackle challenging audio problems such as universal blind source separation, interactive audio editing, audio texture synthesis, and audio co-separation. To understand the robustness of the deep audio prior, we construct a benchmark dataset \emph{Universal-150} for universal sound source separation with a diverse set of sources. We show superior audio results than previous work on both qualitative and quantitative evaluations. We also perform thorough ablation study to validate our design choices.
Code (1)
Tasks
blind source separationTexture SynthesisSimilar Papers 제목 키워드 기반
Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors
In this paper, we introduce a simple and novel framework for one-shot audio-driven talking head generation. Unlike prior works that require additional driving sources for controlled synthesis in a deterministic manner, w…
Talking Head GenerationIteraTTA: An interface for exploring both text prompts and audio priors in generating music with text-to-audio models
Recent text-to-audio generation techniques have the potential to allow novice users to freely generate music audio. Even if they do not have musical knowledge, such as about chord progressions and instruments, users can …
Audio GenerationMusic GenerationDeep Video Inpainting Guided by Audio-Visual Self-Supervision
Humans can easily imagine a scene from auditory information based on their prior knowledge of audio-visual events. In this paper, we mimic this innate human ability in deep learning models to improve the quality of video…
audio-visual learningVideo InpaintingOn the Design of Deep Priors for Unsupervised Audio Restoration
Unsupervised deep learning methods for solving audio restoration problems extensively rely on carefully tailored neural architectures that carry strong inductive biases for defining priors in the time or spectral domain.…
Audio DenoisingDenoisingDeep Audio Waveform Prior
Convolutional neural networks contain strong priors for generating natural looking images [1]. These priors enable image denoising, super resolution, and inpainting in an unsupervised manner. Previous attempts to demonst…
Audio inpaintingAudio Source SeparationDenoisingImage Denoising+1