# EEND-M2F: Masked-attention mask transformers for speaker diarization

arXiv: https://arxiv.org/abs/2401.12600 · HTML: https://mlsanity.com/paper/2401.12600/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jan 2024.

## Built on by (most cited first, 3 of 3)

- [Mamba-based Segmentation Model for Speaker Diarization](https://mlsanity.com/paper/2410.06459/) (2024)
- [Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm](https://mlsanity.com/paper/2506.02610/) (2025)
- [SAGE-LD: Towards Scalable and Generalizable End-to-End Language Diarization via Simulated Data Augmentation](https://mlsanity.com/paper/2510.00582/) (2025)

## Abstract (arXiv)

In this paper, we make the explicit connection between image segmentation methods and end-to-end diarization methods. From these insights, we propose a novel, fully end-to-end diarization model, EEND-M2F, based on the Mask2Former architecture. Speaker representations are computed in parallel using a stack of transformer decoders, in which irrelevant frames are explicitly masked from the cross attention using predictions from previous layers. EEND-M2F is lightweight, efficient, and truly end-to-end, as it does not require any additional diarization, speaker verification, or segmentation models to run, nor does it require running any clustering algorithms. Our model achieves state-of-the-art performance on several public datasets, such as AMI, AliMeeting and RAMC. Most notably our DER of 16.07% on DIHARD-III is the first major improvement upon the challenge winning system.