Visual speaker authentication with random prompt texts by a dual-task CNN framework

作者：

Highlights：

• User authentication with liveness detection based on identity & random prompt text.

• Propose a dual-task DCNN based approach for visual speaker authentication.

• Achieve excellent visual speaker authentication performance.

摘要

•User authentication with liveness detection based on identity & random prompt text.•Propose a dual-task DCNN based approach for visual speaker authentication.•Achieve excellent visual speaker authentication performance.

论文关键词：Visual speaker authentication,Deep convolutional neural network,Multi-tasks learning,Liveness detection

论文评审过程：Received 4 November 2017, Revised 18 May 2018, Accepted 6 June 2018, Available online 20 June 2018, Version of Record 20 June 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.06.005