BPCNN: Bi-Point Input for Convolutional Neural Networks in Speaker Spoofing Detection

We propose a method, called bi-point input, for convolutional neural networks (CNNs) that handle variable-length input features (e.g., speech utterances). Feeding input features into a CNN in a mini-batch unit requires that all features in each mini-batch have the same shape. A set of variable-lengt...

Full description

Bibliographic Details

Published in:	Sensors
Main Authors:	Sunghyun Yoon, Ha-Jin Yu
Format:	Article
Language:	English
Published:	MDPI AG 2022-06-01
Subjects:	bidirectional feature segmentation bi-point input convolutional neural network (CNN) spoofing detection variable-length features
Online Access:	https://www.mdpi.com/1424-8220/22/12/4483