Audio inpainting

LowDDAWP-Net: Low-Resolution Double Deep Audio Waveform Prior Network for Audio Systems Reliability Defence

Kai Chen, Yikun Zhang, Jiasong Wu, J. Coatrieux, Yang Chen•Sun Nov 30 2025

Improving the information reliability of the audio system is critical to safeguarding the security of the audio system. Adversarial samples crafted by in-the-wild attackers by introducing perturbations to the audio become a severe threat to the trustworthiness of deep learning-based classifiers. To achieve dynamic defence against audio adversarial sample attacks, a low-resolution double deep audio waveform prior network (LowDDAWP-Net) for audio systems reliability defence is proposed. Specifically, LowDDAWP-Net consists of a noise audio prior extraction module (<inline-formula><tex-math notation="LaTeX">$\mathbf{DAWP}_{\mathbf{noise}}$</tex-math></inline-formula>), an speech prior extraction module (<inline-formula><tex-math notation="LaTeX">$\mathbf{DAWP}_{\mathbf{speech}}$</tex-math></inline-formula>), a low-resolution extraction module (LREM), and a voice activity detection module (VADM). The role of the VADM is to automatically detect voice activity signals and silent signals from the audio signal. <inline-formula><tex-math notation="LaTeX">$\mathbf{DAWP}_{\mathbf{speech}}$</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">$\mathbf{DAWP}_{\mathbf{noise}}$</tex-math></inline-formula> are encoder–decoders with the same architecture. The encoder extracts the superficial features of the input audio, and the decoder performs temporal fusion to form high-dimensional features and reconstructs them into waveform signals. A LREM is employed to extract low-resolution audio to facilitate the encoder–decoder to perform detail on low-resolution audio and to speed up the recovery of DAWP networks to high resolution. The adversarial samples generated by several diverse attack state-of-the-art on three different datasets and their corresponding benign samples form a novel private dataset. The qualitative and quantitative results of the novel private dataset demonstrate the effectiveness and superiority of LowDDAWP-Net.

0 0

Paper Graph

Audio inpainting | State-of-the-Art

Benchmarks

Libraries

Datasets

Subtasks

Most implemented papers

GACELA: A Generative Adversarial Context Encoder for Long Audio Inpainting of Music

Content

Flexible framework for audio reconstruction

Algorithms for audio inpainting based on probabilistic nonnegative matrix factorization

Audio Inpainting of Music by Means of Neural Networks

Audio inpainting with generative adversarial network

Approximal operator with application to audio inpainting

LowDDAWP-Net: Low-Resolution Double Deep Audio Waveform Prior Network for Audio Systems Reliability Defence

Solving Audio Inverse Problems with a Diffusion Model

Msanii: High Fidelity Music Synthesis on a Shoestring Budget

Diffusion-Based Audio Inpainting