WavInWav: Time-domain Speech Hiding via Invertible Neural Network
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918153760538624 |
|---|---|
| author | Fan, Wei Chen, Kejiang Wang, Xiangkun Zhang, Weiming Yu, Nenghai |
| author_facet | Fan, Wei Chen, Kejiang Wang, Xiangkun Zhang, Weiming Yu, Nenghai |
| contents | Data hiding is essential for secure communication across digital media, and recent advances in Deep Neural Networks (DNNs) provide enhanced methods for embedding secret information effectively. However, previous audio hiding methods often result in unsatisfactory quality when recovering secret audio, due to their inherent limitations in the modeling of time-frequency relationships. In this paper, we explore these limitations and introduce a new DNN-based approach. We use a flow-based invertible neural network to establish a direct link between stego audio, cover audio, and secret audio, enhancing the reversibility of embedding and extracting messages. To address common issues from time-frequency transformations that degrade secret audio quality during recovery, we implement a time-frequency loss on the time-domain signal. This approach not only retains the benefits of time-frequency constraints but also enhances the reversibility of message recovery, which is vital for practical applications. We also add an encryption technique to protect the hidden data from unauthorized access. Experimental results on the VCTK and LibriSpeech datasets demonstrate that our method outperforms previous approaches in terms of subjective and objective metrics and exhibits robustness to various types of noise, suggesting its utility in targeted secure communication scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02915 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WavInWav: Time-domain Speech Hiding via Invertible Neural Network Fan, Wei Chen, Kejiang Wang, Xiangkun Zhang, Weiming Yu, Nenghai Sound Artificial Intelligence Cryptography and Security Machine Learning Audio and Speech Processing Data hiding is essential for secure communication across digital media, and recent advances in Deep Neural Networks (DNNs) provide enhanced methods for embedding secret information effectively. However, previous audio hiding methods often result in unsatisfactory quality when recovering secret audio, due to their inherent limitations in the modeling of time-frequency relationships. In this paper, we explore these limitations and introduce a new DNN-based approach. We use a flow-based invertible neural network to establish a direct link between stego audio, cover audio, and secret audio, enhancing the reversibility of embedding and extracting messages. To address common issues from time-frequency transformations that degrade secret audio quality during recovery, we implement a time-frequency loss on the time-domain signal. This approach not only retains the benefits of time-frequency constraints but also enhances the reversibility of message recovery, which is vital for practical applications. We also add an encryption technique to protect the hidden data from unauthorized access. Experimental results on the VCTK and LibriSpeech datasets demonstrate that our method outperforms previous approaches in terms of subjective and objective metrics and exhibits robustness to various types of noise, suggesting its utility in targeted secure communication scenarios. |
| title | WavInWav: Time-domain Speech Hiding via Invertible Neural Network |
| topic | Sound Artificial Intelligence Cryptography and Security Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2510.02915 |