# Shared Multi-modal Embedding Space for Face-Voice Association

arXiv: https://arxiv.org/abs/2512.04814 · HTML: https://mlsanity.com/paper/2512.04814/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Builds on (most cited first, 8 of 8)

- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [Fusion and Orthogonal Projection for Improved Face-Voice Association](https://mlsanity.com/paper/2112.10483/) (2021)
- [Speaker recognition with two-step multi-modal deep cleansing](https://mlsanity.com/paper/2210.15903/) (2022)
- [Face-voice Association in Multilingual Environments (FAME) 2026 Challenge Evaluation Plan](https://mlsanity.com/paper/2508.04592/) (2025)
- [Multi-Stage Face-Voice Association Learning with Keynote Speaker Diarization](https://mlsanity.com/paper/2407.17902/) (2024)

## Built on by (most cited first, 2 of 2)

- [Linking Faces and Voices Across Languages: Insights from the FAME 2026 Challenge](https://mlsanity.com/paper/2512.20376/) (2025)
- [POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan](https://mlsanity.com/paper/2603.24569/) (2026)

## Abstract (arXiv)

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%.