POLY-SIM: POLYglot Speaker Identification with Missing Modality Grand Challenge 2026

Muhammad Saad Saeed, Marta Moscati, Marina Zanoni, Mubashir Noman, Rohan Kumar Das, Monorama Swain, Yufang Hou, Elisabeth Andre, Khalid Malik, Markus Schedl, Shah Nawaz

Keywords: Multimodal learning, Missing modality, Cross-lingual

Abstract: Multimodal speaker identification systems rely on the availability of complete modalities. However, visual information may be unavailable in real-world scenarios. Additionally, multilingual scenarios may introduce various challenges due to the different semantics of multiple languages. To investigate these issues, we are organizing grand challenge with multimodal speaker identification evaluation protocol under challenging and realistic missing-modality and cross-lingual conditions. To the best of our knowledge, this challenge is the first to investigate speaker identification simultaneously under missing-modality and cross-lingual conditions; thereby paving a new task for robust multimodal speaker identification.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 4