Multi-Channel Replay Speech Detection Using an Adaptive Learnable Beamformer
Replay attacks belong to the class of severe threats against voice-controlled systems, exploiting the easy accessibility of speech signals by recorded and replayed speech to grant unauthorized access to sensitive data. In this work, we propose a multi-channel neural network architecture called M-ALR...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Open Journal of Signal Processing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10994395/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849715201844183040 |
|---|---|
| author | Michael Neri Tuomas Virtanen |
| author_facet | Michael Neri Tuomas Virtanen |
| author_sort | Michael Neri |
| collection | DOAJ |
| description | Replay attacks belong to the class of severe threats against voice-controlled systems, exploiting the easy accessibility of speech signals by recorded and replayed speech to grant unauthorized access to sensitive data. In this work, we propose a multi-channel neural network architecture called M-ALRAD for the detection of replay attacks based on spatial audio features. This approach integrates a learnable adaptive beamformer with a convolutional recurrent neural network, allowing for joint optimization of spatial filtering and classification. Experiments have been carried out on the ReMASC dataset, which is a state-of-the-art multi-channel replay speech detection dataset encompassing four microphones with diverse array configurations and four environments. Results on the ReMASC dataset show the superiority of the approach compared to the state-of-the-art and yield substantial improvements for challenging acoustic environments. In addition, we demonstrate that our approach is able to better generalize to unseen environments with respect to prior studies. |
| format | Article |
| id | doaj-art-a843309f1f2e4c4e89cf545a0bbafc3d |
| institution | DOAJ |
| issn | 2644-1322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Signal Processing |
| spelling | doaj-art-a843309f1f2e4c4e89cf545a0bbafc3d2025-08-20T03:13:29ZengIEEEIEEE Open Journal of Signal Processing2644-13222025-01-01653053510.1109/OJSP.2025.356875810994395Multi-Channel Replay Speech Detection Using an Adaptive Learnable BeamformerMichael Neri0https://orcid.org/0000-0002-6212-9139Tuomas Virtanen1https://orcid.org/0000-0002-4604-9729Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, FinlandFaculty of Information Technology and Communication Sciences, Tampere University, Tampere, FinlandReplay attacks belong to the class of severe threats against voice-controlled systems, exploiting the easy accessibility of speech signals by recorded and replayed speech to grant unauthorized access to sensitive data. In this work, we propose a multi-channel neural network architecture called M-ALRAD for the detection of replay attacks based on spatial audio features. This approach integrates a learnable adaptive beamformer with a convolutional recurrent neural network, allowing for joint optimization of spatial filtering and classification. Experiments have been carried out on the ReMASC dataset, which is a state-of-the-art multi-channel replay speech detection dataset encompassing four microphones with diverse array configurations and four environments. Results on the ReMASC dataset show the superiority of the approach compared to the state-of-the-art and yield substantial improvements for challenging acoustic environments. In addition, we demonstrate that our approach is able to better generalize to unseen environments with respect to prior studies.https://ieeexplore.ieee.org/document/10994395/Replay attackphysical accessbeamformingspatial audiovoice anti-spoofing |
| spellingShingle | Michael Neri Tuomas Virtanen Multi-Channel Replay Speech Detection Using an Adaptive Learnable Beamformer IEEE Open Journal of Signal Processing Replay attack physical access beamforming spatial audio voice anti-spoofing |
| title | Multi-Channel Replay Speech Detection Using an Adaptive Learnable Beamformer |
| title_full | Multi-Channel Replay Speech Detection Using an Adaptive Learnable Beamformer |
| title_fullStr | Multi-Channel Replay Speech Detection Using an Adaptive Learnable Beamformer |
| title_full_unstemmed | Multi-Channel Replay Speech Detection Using an Adaptive Learnable Beamformer |
| title_short | Multi-Channel Replay Speech Detection Using an Adaptive Learnable Beamformer |
| title_sort | multi channel replay speech detection using an adaptive learnable beamformer |
| topic | Replay attack physical access beamforming spatial audio voice anti-spoofing |
| url | https://ieeexplore.ieee.org/document/10994395/ |
| work_keys_str_mv | AT michaelneri multichannelreplayspeechdetectionusinganadaptivelearnablebeamformer AT tuomasvirtanen multichannelreplayspeechdetectionusinganadaptivelearnablebeamformer |