We present MaskedFOP, a system for closed-set polyglot speaker identification under two simultaneous challenges: the face modality is entirely absent at test time, and speech comes from Urdu, a language unseen during face-supervised training. The system integrates three complementary mechanisms. First, a modality-dropout dual-head network built on the Fusion and Orthogonal Projection (FOP) backbone forces the audio branch to develop independent discriminative power via per-sample face masking, ensuring that the audio encoder remains capable when face is absent. Second, two MaskedFOP instances trained on Emphasized Channel Attention, Propagation, and Aggregation in Time Delay Neural Network (ECAPA-TDNN) features with different random seeds produce complementary audio embeddings whose element-wise average yields a more robust 512-dimensional representation than any single model. Third, a two-stage cascaded inference procedure first refines multimodal labels through a fused Graph Label Propagation (GLP) pass (Stage 1), then assigns audio-only labels by cosine nearest-centroid (Stage 2), replacing the 70 sparse training prototypes with ~1,500 in-domain test-set centroids from Stage 1. Submitted to the POLY-SIM 2026 Grand Challenge, the system achieves a mean P-accuracy of 0.9989, placing first among all submissions evaluated on the challenge server. An ablation identifies cascaded seeding as the single largest gain (>8 pp on P4/P6). The code is available at https://github.com/Ayoub-Elkhouzari/POLY-SIM2026.

翻译：我们提出MaskedFOP系统，用于应对双重挑战下的封闭集多语说话人识别问题：测试时人脸模态完全缺失，且语音来自乌尔都语（一种在面部监督训练中未见过的语言）。该系统整合了三种互补机制。首先，基于融合与正交投影（FOP）骨干构建的模态丢弃双头网络，通过逐样本面部掩码强制音频分支发展独立判别能力，确保音频编码器在人脸缺失时仍保有性能。其次，两个在不同随机种子下利用强调通道注意力、传播与聚合的时延神经网络（ECAPA-TDNN）特征训练的MaskedFOP实例产生互补的音频嵌入，其逐元素平均相比任何单一模型都能获得更鲁棒的512维表征。第三，两阶段级联推理流程首先通过融合图标签传播（GLP）过程（阶段1）精炼多模态标签，随后通过余弦近质心（阶段2）分配纯音频标签，用阶段1中约1500个域内测试集质心替代70个稀疏训练原型。该系统提交至POLY-SIM 2026大挑战赛，在评测服务器上以0.9989的平均P-accuracy排名第一。消融实验表明，级联播种是最大增益来源（在P4/P6上提升>8个百分点）。代码发布在https://github.com/Ayoub-Elkhouzari/POLY-SIM2026。