A Deep Learning-based Audio-in-Image Watermarking Scheme

TL;DR

This paper introduces a deep learning-based method for embedding and extracting audio watermarks within images, achieving high fidelity and robustness through an unsupervised neural network architecture and a similarity network for recognition under distortions.

Contribution

It proposes a novel neural network architecture for unsupervised audio-in-image watermarking with robustness to distortions, advancing the capabilities of covert audio embedding.

Findings

High fidelity in watermark embedding and extraction

Robustness against distortions demonstrated

Effective recognition of watermarks under various conditions

Abstract

This paper presents a deep learning-based audio-in-image watermarking scheme. Audio-in-image watermarking is the process of covertly embedding and extracting audio watermarks on a cover-image. Using audio watermarks can open up possibilities for different downstream applications. For the purpose of implementing an audio-in-image watermarking that adapts to the demands of increasingly diverse situations, a neural network architecture is designed to automatically learn the watermarking process in an unsupervised manner. In addition, a similarity network is developed to recognize the audio watermarks under distortions, therefore providing robustness to the proposed method. Experimental results have shown high fidelity and robustness of the proposed blind audio-in-image watermarking scheme.