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...
Main Authors: | Sunghyun Yoon, Ha-Jin Yu |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-06-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/12/4483 |
Similar Items
-
A hybrid deep learning technique for spoofing website URL detection in real-time applications
by: Bridget C. Ujah-Ogbuagu, et al.
Published: (2024-01-01) -
Algorithm of face anti-spoofing based on pseudo-negative features generation
by: Yukun Ma, et al.
Published: (2024-04-01) -
A Survey of GNSS Spoofing and Anti-Spoofing Technology
by: Lianxiao Meng, et al.
Published: (2022-09-01) -
Detection of face spoofing attacks on biometric identification systems
by: D. Zhuravlov, et al.
Published: (2023-05-01) -
Directional Difference Convolution and Its Application on Face Anti-Spoofing
by: Mingye Yang, et al.
Published: (2022-01-01)