# Encoder-Decoder Based Attractors for End-to-End Neural Diarization

arXiv: https://arxiv.org/abs/2106.10654 · HTML: https://mlsanity.com/paper/2106.10654/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2021.

## Built on by (most cited first, 20 of 20)

- [Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems](https://mlsanity.com/paper/2409.06656/) (2024)
- [Online Neural Diarization of Unlimited Numbers of Speakers Using Global and Local Attractors](https://mlsanity.com/paper/2206.02432/) (2022)
- [Improving the Naturalness of Simulated Conversations for End-to-End Neural Diarization](https://mlsanity.com/paper/2204.11232/) (2022)
- [Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarization](https://mlsanity.com/paper/2208.13085/) (2022)
- [Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder](https://mlsanity.com/paper/2508.20474/) (2025)
- [Neural Diarization with Non-autoregressive Intermediate Attractors](https://mlsanity.com/paper/2303.06806/) (2023)
- [Content Anonymization for Privacy in Long-form Audio](https://mlsanity.com/paper/2510.12780/) (2025)
- [Online speaker diarization of meetings guided by speech separation](https://mlsanity.com/paper/2402.00067/) (2024)
- [Late Audio-Visual Fusion for In-The-Wild Speaker Diarization](https://mlsanity.com/paper/2211.01299/) (2022)
- [ASoBO: Attentive Beamformer Selection for Distant Speaker Diarization in Meetings](https://mlsanity.com/paper/2406.03251/) (2024)
- [Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matching](https://mlsanity.com/paper/2409.04859/) (2024)
- [MK-SGC-SC: Multiple Kernel Guided Sparse Graph Construction in Spectral Clustering for Unsupervised Speaker Diarization](https://mlsanity.com/paper/2601.19946/) (2026)
- [Diarisation using location tracking with agglomerative clustering](https://mlsanity.com/paper/2109.10598/) (2021)
- [Joint speaker diarisation and tracking in switching state-space model](https://mlsanity.com/paper/2109.11140/) (2021)
- [Mutual Learning of Single- and Multi-Channel End-to-End Neural Diarization](https://mlsanity.com/paper/2210.03459/) (2022)
- [Leveraging Speaker Embeddings in End-to-End Neural Diarization for Two-Speaker Scenarios](https://mlsanity.com/paper/2407.01317/) (2024)
- [Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm](https://mlsanity.com/paper/2506.02610/) (2025)
- [Improving Neural Diarization through Speaker Attribute Attractors and Local Dependency Modeling](https://mlsanity.com/paper/2506.05593/) (2025)
- [Mitigating Intra-Speaker Variability in Diarization with Style-Controllable Speech Augmentation](https://mlsanity.com/paper/2509.14632/) (2025)
- [Neural Multichannel Distant Speaker Diarization with Heavy-tailed Source Separation Model](https://mlsanity.com/paper/2609.12154/) (2026)

## Abstract (arXiv)

This paper investigates an end-to-end neural diarization (EEND) method for an unknown number of speakers. In contrast to the conventional cascaded approach to speaker diarization, EEND methods are better in terms of speaker overlap handling. However, EEND still has a disadvantage in that it cannot deal with a flexible number of speakers. To remedy this problem, we introduce encoder-decoder-based attractor calculation module (EDA) to EEND. Once frame-wise embeddings are obtained, EDA sequentially generates speaker-wise attractors on the basis of a sequence-to-sequence method using an LSTM encoder-decoder. The attractor generation continues until a stopping condition is satisfied; thus, the number of attractors can be flexible. Diarization results are then estimated as dot products of the attractors and embeddings. The embeddings from speaker overlaps result in larger dot product values with multiple attractors; thus, this method can deal with speaker overlaps. Because the maximum number of output speakers is still limited by the training set, we also propose an iterative inference method to remove this restriction. Further, we propose a method that aligns the estimated diarization results with the results of an external speech activity detector, which enables fair comparison against cascaded approaches. Extensive evaluations on simulated and real datasets show that EEND-EDA outperforms the conventional cascaded approach.