no code implementations • 3 Jan 2024 • Danwei Cai, Zexin Cai, Ming Li
Specifically, a teacher model continually refines pseudo labels through online clustering, providing dynamic supervision signals to train the student model.
no code implementations • 6 Sep 2023 • Danwei Cai, Ming Li
This paper explores the use of ASR-pretrained Conformers for speaker verification, leveraging their strengths in modeling speech signals.
no code implementations • 18 Jun 2022 • Danwei Cai, Zexin Cai, Ming Li
An automatic speaker verification system aims to verify the speaker identity of a speech signal.
no code implementations • 7 Sep 2021 • Danwei Cai, Ming Li
Taking advantage of DNN's ability to learn from data with label noise, we propose to cluster the speaker embedding obtained from the previous speaker network and use the subsequent class assignments as pseudo labels to train a new DNN.
no code implementations • 5 Sep 2021 • Weiqing Wang, Danwei Cai, Qingjian Lin, Lin Yang, Junjie Wang, Jin Wang, Ming Li
This report describes the submission of the DKU-DukeECE-Lenovo team to the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2021 track 4.
no code implementations • 5 Jul 2019 • Weicheng Cai, Haiwei Wu, Danwei Cai, Ming Li
This paper describes our DKU replay detection system for the ASVspoof 2019 challenge.
no code implementations • 20 Feb 2019 • Weicheng Cai, Danwei Cai, Shen Huang, Ming Li
In this paper, we present an end-to-end language identification framework, the attention-based Convolutional Neural Network-Bidirectional Long-short Term Memory (CNN-BLSTM).
1 code implementation • 9 Sep 2018 • Jinkun Chen, Weicheng Cai, Danwei Cai, Zexin Cai, Haibin Zhong, Ming Li
In this paper, we apply the NetFV and NetVLAD layers for the end-to-end language identification task.