mlsanityData to 7 Oct 2026

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

arXiv 2512.20376 ↗First posted 23 Dec 2025cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Over half of the world's population is bilingual and people often communicate under multilingual scenarios. The Face-Voice Association in Multilingual Environments (FAME) 2026 Challenge, held at ICASSP 2026, focuses on developing methods for face-voice association that are effective when the language at test-time is different than the training one. This report provides a brief summary of the challenge.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 16 of its 22 references that are in the map. First posted on arXiv 23 Dec 2025.

Builds on

16 of 22 references.

References · 16

  1. 2018Seeing Voices and Hearing Faces: Cross-modal biometric matchingcited by 60
  2. 2018Learnable PINs: Cross-Modal Embeddings for Person Identitycited by 60
  3. 2019Utterance-level Aggregation For Speaker Recognition In The Wildcited by 49
  4. 2021Fusion and Orthogonal Projection for Improved Face-Voice Associationcited by 29
  5. 2020Cross-modal Speaker Verification and Recognition: A Multilingual Perspectivecited by 26
  6. 2020Audio-visual Speaker Recognition with a Cross-modal Discriminative Networkcited by 24
  7. 2019Deep Latent Space Learning for Cross-modal Mapping of Audio and Visual Signalscited by 20
  8. 2023Single-branch Network for Multimodal Trainingcited by 13
  9. 2023Speaker Recognition in Realistic Scenario Using Multimodal Datacited by 9
  10. 2025PAEFF: Precise Alignment and Enhanced Gated Feature Fusion for Face-Voice Associationcited by 9
  11. 2025Face-voice Association in Multilingual Environments (FAME) 2026 Challenge Evaluation Plancited by 6
  12. 2024Face-voice Association in Multilingual Environments (FAME) Challenge 2024 Evaluation Plancited by 4
4 more
  1. 2025Towards Language-Independent Face-Voice Association with Multimodal Foundation Modelscited by 2
  2. 2025Shared Multi-modal Embedding Space for Face-Voice Associationcited by 2
  3. 2025RFOP: Rethinking Fusion and Orthogonal Projection for Face-Voice Associationcited by 1
  4. 2025XM-ALIGN: Unified Cross-Modal Embedding Alignment for Face-Voice Associationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Face-Voice Association with Inductive Bias for Maximum Class Separationcited by 1
  2. 2026POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plancited by 1
  3. 2026AMR: Adaptive Modality Routing for Multimodal Polyglot Speaker Identificationcited by 1
  4. 2026Learning Speaker Identity Beyond Language and Modality Constraints: Insights from the POLY-SIM 2026 Challengecited by 0
  5. 2026Face-voice Association across LAnguages and Gender (FLAG) 2027 Challenge Evaluation Plancited by 0