THUEE system description for NIST 2020 SRE CTS challenge
Sound
2022-10-13 v1 Artificial Intelligence
Audio and Speech Processing
Signal Processing
Abstract
This paper presents the system description of the THUEE team for the NIST 2020 Speaker Recognition Evaluation (SRE) conversational telephone speech (CTS) challenge. The subsystems including ResNet74, ResNet152, and RepVGG-B2 are developed as speaker embedding extractors in this evaluation. We used combined AM-Softmax and AAM-Softmax based loss functions, namely CM-Softmax. We adopted a two-staged training strategy to further improve system performance. We fused all individual systems as our final submission. Our approach leads to excellent performance and ranks 1st in the challenge.
Keywords
Cite
@article{arxiv.2210.06111,
title = {THUEE system description for NIST 2020 SRE CTS challenge},
author = {Yu Zheng and Jinghan Peng and Miao Zhao and Yufeng Ma and Min Liu and Xinyue Ma and Tianyu Liang and Tianlong Kong and Liang He and Minqiang Xu},
journal= {arXiv preprint arXiv:2210.06111},
year = {2022}
}
Comments
3 pages, 1 table; System desciption of NIST 2020 SRE CTS challenge