Yu-Jia Zhang


2021

pdf bib
Discussion on domain generalization in the cross-device speaker verification system
Wei-Ting Lin | Yu-Jia Zhang | Chia-Ping Chen | Chung-Li Lu | Bo-Cheng Chan
Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)

In this paper, we use domain generalization to improve the performance of the cross-device speaker verification system. Based on a trainable speaker verification system, we use domain generalization algorithms to fine-tune the model parameters. First, we use the VoxCeleb2 dataset to train ECAPA-TDNN as a baseline model. Then, use the CHT-TDSV dataset and the following domain generalization algorithms to fine-tune it: DANN, CDNN, Deep CORAL. Our proposed system tests 10 different scenarios in the NSYSU-TDSV dataset, including a single device and multiple devices. Finally, in the scenario of multiple devices, the best equal error rate decreased from 18.39 in the baseline to 8.84. Successfully achieved cross-device identification on the speaker verification system.

2020

pdf bib
NSYSU+CHT 團隊於 2020 遠場語者驗證比賽之語者驗證系統 (NSYSU+CHT Speaker Verification System for Far-Field Speaker Verification Challenge 2020)
Yu-Jia Zhang | Chia-Ping Chen | Shan-Wen Hsiao | Bo-Cheng Chan | Chung-li Lu
International Journal of Computational Linguistics & Chinese Language Processing, Volume 25, Number 2, December 2020

pdf bib
NSYSU+CHT Speaker Verification System for Far-Field Speaker Verification Challenge 2020
Yu-Jia Zhang | Chia-Ping Chen
Proceedings of the 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020)