Multi-Channel Replay Speech Detection using Acoustic Maps
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916031572738048 |
|---|---|
| author | Neri, Michael Virtanen, Tuomas |
| author_facet | Neri, Michael Virtanen, Tuomas |
| contents | Replay attacks remain a critical vulnerability for automatic speaker verification systems, particularly in real-time voice assistant applications. In this work, we propose acoustic maps as a novel spatial feature representation for replay speech detection from multi-channel recordings. Derived from classical beamforming over discrete azimuth and elevation grids, acoustic maps encode directional energy distributions that reflect physical differences between human speech radiation and loudspeaker-based replay. A lightweight convolutional neural network is designed to operate on this representation, achieving competitive performance on the ReMASC dataset with approximately 6k trainable parameters. Experimental results show that acoustic maps provide a compact and physically interpretable feature space for replay attack detection across different devices and acoustic environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16399 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multi-Channel Replay Speech Detection using Acoustic Maps Neri, Michael Virtanen, Tuomas Audio and Speech Processing Machine Learning Sound Replay attacks remain a critical vulnerability for automatic speaker verification systems, particularly in real-time voice assistant applications. In this work, we propose acoustic maps as a novel spatial feature representation for replay speech detection from multi-channel recordings. Derived from classical beamforming over discrete azimuth and elevation grids, acoustic maps encode directional energy distributions that reflect physical differences between human speech radiation and loudspeaker-based replay. A lightweight convolutional neural network is designed to operate on this representation, achieving competitive performance on the ReMASC dataset with approximately 6k trainable parameters. Experimental results show that acoustic maps provide a compact and physically interpretable feature space for replay attack detection across different devices and acoustic environments. |
| title | Multi-Channel Replay Speech Detection using Acoustic Maps |
| topic | Audio and Speech Processing Machine Learning Sound |
| url | https://arxiv.org/abs/2602.16399 |