paper-with-me

홈 › Papers

Deep Audio Prior

2019-12-21 · Yapeng Tian, Chenliang Xu, DIngzeyu Li

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.

📄 PDF Abstract BibTeX arXiv:1912.10292

Code (1)

adobe/Deep-Audio-Prior pytorch

Tasks

blind source separationTexture Synthesis

Similar Papers 제목 키워드 기반

Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors

2022-12-07 · ICCV 2023 1 · Zhentao Yu, Zixin Yin, Deyu Zhou, Duomin Wang 외

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 Generation

IteraTTA: An interface for exploring both text prompts and audio priors in generating music with text-to-audio models

2023-07-24 · Hiromu Yakura, Masataka Goto

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 Generation

Deep Video Inpainting Guided by Audio-Visual Self-Supervision

2023-10-11 · Kyuyeon Kim, Junsik Jung, Woo Jae Kim, Sung-Eui Yoon

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 Inpainting

On the Design of Deep Priors for Unsupervised Audio Restoration

2021-04-14 · Vivek Sivaraman Narayanaswamy, Jayaraman J. Thiagarajan, Andreas Spanias

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 DenoisingDenoising

Deep Audio Waveform Prior

2022-07-21 · Arnon Turetzky, Tzvi Michelson, Yossi Adi, Shmuel Peleg

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