Deep Audio Prior

Abstract

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 *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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytian2019deep

Related papers

• PERSA+: A Deep Learning Front-end For Context-agnostic Audio Classification (2021)0.00
• Audio Source Separation Via Multi-scale Learning With Dilated Dense U-nets (2019)0.00
• APPLADE: Adjustable Plug-and-play Audio Declipper Combining DNN With Sparse Optimization (2022)5.84
• Audio-based Music Classification With Densenet And Data Augmentation (2019)10.48
• Mmdenselstm: An Efficient Combination Of Convolutional And Recurrent Neural Networks For Audio Source Separation (2018)15.28
• D3net: Densely Connected Multidilated Densenet For Music Source Separation (2020)0.00
• Can We Trust Deep Speech Prior? (2020)2.26
• Audio Concept Classification With Hierarchical Deep Neural Networks (2017)0.00