Noise-to-mask Ratio Loss for Deep Neural Network based Audio Watermarking
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913570138095616 |
|---|---|
| author | Moritz, Martin Olán, Toni Virtanen, Tuomas |
| author_facet | Moritz, Martin Olán, Toni Virtanen, Tuomas |
| contents | Digital audio watermarking consists in inserting a message into audio signals in a transparent way and can be used to allow automatic recognition of audio material and management of the copyrights. We propose a perceptual loss function to be used in deep neural network based audio watermarking systems. The loss is based on the noise-to-mask ratio (NMR), which is a model of the psychoacoustic masking effect characteristic of the human ear. We use the NMR loss between marked and host signals to train the deep neural models and we evaluate the objective quality with PEAQ and the subjective quality with a MUSHRA test. Both objective and subjective tests show that models trained with NMR loss generate more transparent watermarks than models trained with the conventionally used MSE loss |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_15553 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Noise-to-mask Ratio Loss for Deep Neural Network based Audio Watermarking Moritz, Martin Olán, Toni Virtanen, Tuomas Audio and Speech Processing Sound Digital audio watermarking consists in inserting a message into audio signals in a transparent way and can be used to allow automatic recognition of audio material and management of the copyrights. We propose a perceptual loss function to be used in deep neural network based audio watermarking systems. The loss is based on the noise-to-mask ratio (NMR), which is a model of the psychoacoustic masking effect characteristic of the human ear. We use the NMR loss between marked and host signals to train the deep neural models and we evaluate the objective quality with PEAQ and the subjective quality with a MUSHRA test. Both objective and subjective tests show that models trained with NMR loss generate more transparent watermarks than models trained with the conventionally used MSE loss |
| title | Noise-to-mask Ratio Loss for Deep Neural Network based Audio Watermarking |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2408.15553 |