works on
audio-visual fusion 1missing modalities 1multilingual speakers 1multimodal learning 1robustness 1speaker identification 1

From the 1 of 2 linked papers with an AI index.

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

Learning Speaker Identity Beyond Language and Modality Constraints: Insights from the POLY-SIM 2026 Challenge

Marta Moscati, Muhammad Saad Saeed, Marina Zanoni +9

The paper describes the POLY-SIM 2026 challenge, which focuses on developing multimodal speaker identification systems that remain robust when audio or visual data are missing and…