Shared Multi-modal Embedding Space for Face-Voice Association

Christopher Simic, Korbinian Riedhammer, Tobias Bocklet
12/4/2025
cs.SDcs.CV

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

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%.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

XM-ALIGN: Unified Cross-Modal Embedding Alignment for Face-Voice Association

85% match1 repo72025

RFOP: Rethinking Fusion and Orthogonal Projection for Face-Voice Association

85% match2025

Linking Faces and Voices Across Languages: Insights from the FAME 2026 Challenge

83% match2025

POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan

82% match2026

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition

82% match1 repo3072024

InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue

82% match2025

Cite this paper

@article{simic2025shared,
  title  = {Shared Multi-modal Embedding Space for Face-Voice Association},
  author = {Christopher Simic and Korbinian Riedhammer and Tobias Bocklet},
  year   = {2025},
  eprint = {2512.04814},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2512.04814v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2512.04814.svg)](https://codeofpaper.com/paper/2512.04814)

Discussion