# Face-Voice Association with Inductive Bias for Maximum Class Separation

arXiv: https://arxiv.org/abs/2601.13651 · HTML: https://mlsanity.com/paper/2601.13651/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?](https://mlsanity.com/paper/2203.09081/) (2022)
- [Seeing Voices and Hearing Faces: Cross-modal biometric matching](https://mlsanity.com/paper/1804.00326/) (2018)
- [Learnable PINs: Cross-Modal Embeddings for Person Identity](https://mlsanity.com/paper/1805.00833/) (2018)
- [Utterance-level Aggregation For Speaker Recognition In The Wild](https://mlsanity.com/paper/1902.10107/) (2019)
- [Orthogonal Projection Loss](https://mlsanity.com/paper/2103.14021/) (2021)
- [Fusion and Orthogonal Projection for Improved Face-Voice Association](https://mlsanity.com/paper/2112.10483/) (2021)
- [Cross-modal Speaker Verification and Recognition: A Multilingual Perspective](https://mlsanity.com/paper/2004.13780/) (2020)
- [Disjoint Mapping Network for Cross-modal Matching of Voices and Faces](https://mlsanity.com/paper/1807.04836/) (2018)
- [Maximum Class Separation as Inductive Bias in One Matrix](https://mlsanity.com/paper/2206.08704/) (2022)
- [Deep Latent Space Learning for Cross-modal Mapping of Audio and Visual Signals](https://mlsanity.com/paper/1909.08685/) (2019)
- [Single-branch Network for Multimodal Training](https://mlsanity.com/paper/2303.06129/) (2023)
- [PAEFF: Precise Alignment and Enhanced Gated Feature Fusion for Face-Voice Association](https://mlsanity.com/paper/2505.17002/) (2025)
- [OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer](https://mlsanity.com/paper/2004.09033/) (2020)
- [Linking Faces and Voices Across Languages: Insights from the FAME 2026 Challenge](https://mlsanity.com/paper/2512.20376/) (2025)
- [Multi-Stage Face-Voice Association Learning with Keynote Speaker Diarization](https://mlsanity.com/paper/2407.17902/) (2024)
- [Target Speech Diarization with Multimodal Prompts](https://mlsanity.com/paper/2406.07198/) (2024)
- [Exploring Robust Face-Voice Matching in Multilingual Environments](https://mlsanity.com/paper/2407.19875/) (2024)
- [Contrastive Learning-based Chaining-Cluster for Multilingual Voice-Face Association](https://mlsanity.com/paper/2408.02025/) (2024)

## Built on by (most cited first, 1 of 1)

- [Face-voice Association across LAnguages and Gender (FLAG) 2027 Challenge Evaluation Plan](https://mlsanity.com/paper/2609.17913/) (2026)

## Abstract (arXiv)

Face-voice association is widely studied in multimodal learning and is approached representing faces and voices with embeddings that are close for a same person and well separated from those of others. Previous work achieved this with loss functions. Recent advancements in classification have shown that the discriminative ability of embeddings can be strengthened by imposing maximum class separation as inductive bias. This technique has never been used in the domain of face-voice association, and this work aims at filling this gap. More specifically, we develop a method for face-voice association that imposes maximum class separation among multimodal representations of different speakers as an inductive bias. Through quantitative experiments we demonstrate the effectiveness of our approach, showing that it achieves SOTA performance on two task formulation of face-voice association. Furthermore, we carry out an ablation study to show that imposing inductive bias is most effective when combined with losses for inter-class orthogonality. To the best of our knowledge, this work is the first that applies and demonstrates the effectiveness of maximum class separation as an inductive bias in multimodal learning; it hence paves the way to establish a new paradigm.