New replay attack detection using iterative adaptive inverse filtering and high frequency band

作者：

Highlights：

• Iterative Adaptive Inverse Filtering extracts the glottal excitation information.

• Excitation source information is extracted from high-frequency band.

• CQCC algorithm is used to extract the feature from high-frequency band.

• Gaussian mixture model is used as a classifier to detect replayed speech.

• The experimental studies done on ASV spoof-2017 version 2.0 database.

摘要

•Iterative Adaptive Inverse Filtering extracts the glottal excitation information.•Excitation source information is extracted from high-frequency band.•CQCC algorithm is used to extract the feature from high-frequency band.•Gaussian mixture model is used as a classifier to detect replayed speech.•The experimental studies done on ASV spoof-2017 version 2.0 database.

论文关键词：Replay attack,Speaker verification,High frequency band,IA-IF,CQCC

论文评审过程：Received 19 May 2020, Revised 5 January 2022, Accepted 20 January 2022, Available online 31 January 2022, Version of Record 1 February 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116597