Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913815024631808 |
|---|---|
| author | Luong, Diep Tran, Minh Gharib, Shayan Drossos, Konstantinos Virtanen, Tuomas |
| author_facet | Luong, Diep Tran, Minh Gharib, Shayan Drossos, Konstantinos Virtanen, Tuomas |
| contents | Privacy preservation has long been a concern in smart acoustic monitoring systems, where speech can be passively recorded along with a target signal in the system's operating environment. In this study, we propose the integration of two commonly used approaches in privacy preservation: source separation and adversarial representation learning. The proposed system learns the latent representation of audio recordings such that it prevents differentiating between speech and non-speech recordings. Initially, the source separation network filters out some of the privacy-sensitive data, and during the adversarial learning process, the system will learn privacy-preserving representation on the filtered signal. We demonstrate the effectiveness of our proposed method by comparing our method against systems without source separation, without adversarial learning, and without both. Overall, our results suggest that the proposed system can significantly improve speech privacy preservation compared to that of using source separation or adversarial learning solely while maintaining good performance in the acoustic monitoring task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_04960 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning Luong, Diep Tran, Minh Gharib, Shayan Drossos, Konstantinos Virtanen, Tuomas Sound Cryptography and Security Machine Learning Audio and Speech Processing Privacy preservation has long been a concern in smart acoustic monitoring systems, where speech can be passively recorded along with a target signal in the system's operating environment. In this study, we propose the integration of two commonly used approaches in privacy preservation: source separation and adversarial representation learning. The proposed system learns the latent representation of audio recordings such that it prevents differentiating between speech and non-speech recordings. Initially, the source separation network filters out some of the privacy-sensitive data, and during the adversarial learning process, the system will learn privacy-preserving representation on the filtered signal. We demonstrate the effectiveness of our proposed method by comparing our method against systems without source separation, without adversarial learning, and without both. Overall, our results suggest that the proposed system can significantly improve speech privacy preservation compared to that of using source separation or adversarial learning solely while maintaining good performance in the acoustic monitoring task. |
| title | Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning |
| topic | Sound Cryptography and Security Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2308.04960 |