论文标题
Thuee系统描述NIST 2020 SRE CTS挑战
THUEE system description for NIST 2020 SRE CTS challenge
论文作者
论文摘要
本文介绍了NIST 2020说话者识别评估（SRE）对话电话演讲（CTS）挑战的Thuee团队的系统描述。在此评估中，开发了包括RESNET74，RESNET152和REPVGG-B2在内的子系统作为嵌入提取器的开发。我们使用了基于AM-Softmax和AAM-SoftMax的组合损失功能，即CM-SoftMax。我们采用了两期培训策略来进一步提高系统性能。我们将所有单个系统融合为我们的最终提交。我们的方法带来了出色的表现，并在挑战中排名第一。
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.
