2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Paper Detail

Paper IDSPE-26.6
Paper Title Replay-Attack Detection using Features with Adaptive Spectro-Temporal Resolution
Authors Meng Liu, Longbiao Wang, Tianjin University, China; Kong Aik Lee, Agency for Science, Technology and Research ‎(A*STAR)‎, Singapore; Xuanda Chen, Chinese Academy of Social Sciences, China; Jianwu Dang, Japan Advanced Institute of Science and Technology, Japan
SessionSPE-26: Speaker Verification Spoofing and Countermeasures
LocationGather.Town
Session Time:Wednesday, 09 June, 15:30 - 16:15
Presentation Time:Wednesday, 09 June, 15:30 - 16:15
Presentation Poster
Topic Speech Processing: [SPE-SPKR] Speaker Recognition and Characterization
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Virtual Presentation  Click here to watch in the Virtual Conference
Abstract Variable-resolution processing aims to improve the feature representation ability by enlarging the local discriminative details. In previous anti-spoofing studies, phones and frequencies were both proven to be sensitive to replay distortion. In this paper, an adaptive spectro-temporal resolution is proposed to obtain the optimal scale in the feature space: the frequency resolution is adaptive to frequency discrimination, while the temporal resolution is adaptive to continuous phones. In the process, phone-frequency F-ratio analysis is applied to investigate the sensitivity divergences to replay distortion among phones and frequencies. Then, attentive filters are designed to automatically adapt to the phone-frequency discrimination. Validation experiments for the proposed method are conducted on two well-acknowledged magnitude and phase features. A comparative analysis on the ASVspoof 2017 V2.0 database demonstrates that our proposed adaptive spectro-temporal resolution method attains considerably higher error reduction rates than the approaches involving the corresponding original resolution features.