| Title | Replay Attack Detection Using Magnitude and Phase Information with Attention-based Adaptive Filters |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Authors | Liu, Meng, Wang, Longbiao, Dang, Jianwu, Nakagawa, Seiichi, Guan, Haotian, Li, Xiangang |
| Conference Name | ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
| Keywords | adaptive filtering, adaptive filters, ASVspoof 2017, attention-based adaptive filters, automatic speech verification systems, conventional feature extraction techniques, Databases, fast Fourier transforms, feature extraction, frequency bands, frequency-domain analysis, high discriminative information, magnitude channel complementary features, magnitude information, Mel frequency cepstral coefficient, Metrics, multichannel feature extraction method, original phase information, phase channel, phase information, pubcrawl, replay attack detection, replay attacks, replay spoofed speech, Resiliency, Scalability, spoofing attacks, Task Analysis, telecommunication security, voice activity detection |
| Abstract | Automatic Speech Verification (ASV) systems are highly vulnerable to spoofing attacks, and replay attack poses the greatest threat among various spoofing attacks. In this paper, we propose a novel multi-channel feature extraction method with attention-based adaptive filters (AAF). Original phase information, discarded by conventional feature extraction techniques after Fast Fourier Transform (FFT), is promising in distinguishing genuine from replay spoofed speech. Accordingly, phase and magnitude information are respectively extracted as phase channel and magnitude channel complementary features in our system. First, we make discriminative ability analysis on full frequency bands with F-ratio methods. Then attention-based adaptive filters are implemented to maximize capturing of high discriminative information on frequency bands, and the results on ASVspoof 2017 challenge indicate that our proposed approach achieved relative error reduction rates of 78.7% and 59.8% on development and evaluation dataset than the baseline method. |
| DOI | 10.1109/ICASSP.2019.8682739 |
| Citation Key | liu_replay_2019 |
Replay Attack Detection Using Magnitude and Phase Information with Attention-based Adaptive Filters