构建共享嵌入空间，实现跨语言人脸与声音关联匹配
Shared Multi-modal Embedding Space for Face-Voice Association
- 分别提取人脸、声音及年龄性别特征，映射到统一嵌入空间
- 采用自适应角度损失训练，平均等错误率降至23.99%
- 适用于多语言环境下的人声-人脸配对任务
FAME 2026挑战包含两个高难度任务：在多语言设置下训练人脸与声音的关联，并在未见过的语言上进行测试。本文方法采用独立的单模态处理流程，分别进行通用人脸与声音特征提取，并额外加入年龄性别特征以支持预测。各单模态特征被投影至共享嵌入空间，并使用自适应角度损失（AAM）进行训练。该方法在FAME 2026挑战中获得第一名，平均等错误率（EER）为23.99%。
原文摘要 · Abstract (English)
The FAME 2026 challenge comprises two demanding tasks: training face-voice associations combined with a multilingual setting that includes testing on languages on which the model was not trained. Our approach consists of separate uni-modal processing pipelines with general face and voice feature extraction, complemented by additional age-gender feature extraction to support prediction. The resulting single-modal features are projected into a shared embedding space and trained with an Adaptive Angular Margin (AAM) loss. Our approach achieved first place in the FAME 2026 challenge, with an average Equal-Error Rate (EER) of 23.99%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。