雷震春(副教授,博士)

发布时间: 2016-04-15 浏览次数: 7428


雷震春,男,1977年生,博士,副教授,2006年12月毕业于浙江大学计算机学院,获博士学位,主持参与多项国家级科研项目。受聘全国研究生教育评估监测专家库专家,全国本科毕业论文(设计)抽检评审专家库专家。担任ICASSP,Interspeech,ICPRTASLP,THMS,KBS,CCSP等会议和期刊审稿人。

 

主要研究领域:说话人识别、语音信号处理、机器学习

 

欢迎各位硕士研究生加入实验室,特别欢迎打算报考985高校博士的同学,实验室提供充分科研指导!

电子邮件:zhenchun.lei@hotmail.com

 

论文:

1. GMM-RESNET2: ENSEMBLE OF GROUP RESNET NETWORKS FOR SYNTHETIC SPEECH DETECTION, in ICASSP 2024, 第一作者, (CCF B类).

2. GMM-RESNEXT: COMBINING GENERATIVE AND DISCRIMINATIVE MODELS FOR SPEAKER VERIFICATION, in ICASSP 2024, 通信作者, 排名2, (CCF B类).

3. Music-Driven Character Dance Video Generation Based on Pre-Trained Diffusion Model, in IJCNN 2024, (CCF C类).

4. Group GMM-ResNet for Detection of Synthetic Speech Attacks, in Interspeech 2023, 第一作者, (CCF C类).

5. Snippet-Level Supervised Contrastive Learning-Based Transformer for Temporal Action Detection, in IJCNN 2023, (CCF C类).

6. TWO-PATH GMM-RESNET AND GMM-SENET FOR ASV SPOOFING DETECTION, in ICASSP 2022, 第一作者, (CCF B类).

7. Multi-Path GMM-MobileNet Based on Attack Algorithms and Codecs for Synthetic Speech and Deepfake Detection, in Interspeech 2022, 通信作者, 排名2, (CCF C类).

8. 基于高斯概率特征的孪生Bi-LSTM模型语音欺骗检测研究,小型微型计算机系统,通信作者,排名2, (CCF B类).

9. Music-to-Dance Generation with Multiple Conformer, in ICMR 2022 (CCF B类).

10. Multi-Scale Cascaded Generator for Music-driven Dance Synthesis, in IJCNN 2022, (CCF C类).

11. Attention Network with GMM Based Feature for ASV Spoofing Detection, in CCBR 2021, 第一作者, (EI).

12. Siamese Convolutional Neural Network Using Gaussian Probability Feature for Spoofing Speech Detection, in InterSpeech 2020, 第一作者, (CCF C类).