Class token and knowledge distillation for multi-head self-attention speaker verification systems-Reference-Cited by-同舟云学术

Class token and knowledge distillation for multi-head self-attention speaker verification systems

Published:2023-03 Issue: Volume:133 Page:103859
ISSN:1051-2004
Container-title:Digital Signal Processing
language:en
Short-container-title:Digital Signal Processing

Author:

Mingote Victoria^ORCID,Miguel Antonio,Ortega Alfonso,Lleida Eduardo

Publisher

Elsevier BV

Subject

Electrical and Electronic Engineering,Signal Processing,Artificial Intelligence,Applied Mathematics,Computer Vision and Pattern Recognition,Statistics, Probability and Uncertainty,Computational Theory and Mathematics

Reference46 articles.

1. DeepFace: closing the gap to human-level performance in face verification;Taigman,2014

2. X-vectors: robust dnn embeddings for speaker recognition;Snyder,2018

3. Deep metric learning using triplet network;Hoffer;Lect. Notes Comput. Sci. (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics),2015

4. Facenet: a unified embedding for face recognition and clustering;Schroff,2015

5. Deep neural network-based speaker embeddings for end-to-end speaker verification;Snyder,2016

Cited by 4 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Hybrid Feature Optimization for Voice Spoof Detection Using CNN-LSTM;Traitement du Signal;2024-04-30

2. Vision transformer-based electronic nose for enhanced mixed gases classification;Measurement Science and Technology;2024-03-21

3. Optimized deep network based spoof detection in automatic speaker verification system;Multimedia Tools and Applications;2023-07-04

4. MCE-ST: Classifying crop stress using hyperspectral data with a multiscale conformer encoder and spectral-based tokens;International Journal of Applied Earth Observation and Geoinformation;2023-04