# BW-EDA-EEND: Streaming End-to-End Neural Speaker Diarization for a Variable Number of Speakers

arXiv: https://arxiv.org/abs/2011.02678 · HTML: https://mlsanity.com/paper/2011.02678/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2020.

## Built on by (most cited first, 11 of 11)

- [A Review of Speaker Diarization: Recent Advances with Deep Learning](https://mlsanity.com/paper/2101.09624/) (2021)
- [Towards Neural Diarization for Unlimited Numbers of Speakers Using Global and Local Attractors](https://mlsanity.com/paper/2107.01545/) (2021)
- [BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications](https://mlsanity.com/paper/2110.05781/) (2021)
- [Online Neural Diarization of Unlimited Numbers of Speakers Using Global and Local Attractors](https://mlsanity.com/paper/2206.02432/) (2022)
- [ASR-Aware End-to-end Neural Diarization](https://mlsanity.com/paper/2202.01286/) (2022)
- [End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations](https://mlsanity.com/paper/2303.12002/) (2023)
- [Speaker Diarization of Scripted Audiovisual Content](https://mlsanity.com/paper/2308.02160/) (2023)
- [Towards Word-Level End-to-End Neural Speaker Diarization with Auxiliary Network](https://mlsanity.com/paper/2309.08489/) (2023)
- [A Review of Common Online Speaker Diarization Methods](https://mlsanity.com/paper/2406.14464/) (2024)
- [O-EENC-SD: Efficient Online End-to-End Neural Clustering for Speaker Diarization](https://mlsanity.com/paper/2512.15229/) (2025)
- [FASTDIAR: Frame-level speaker encoder for Streaming Diarization](https://mlsanity.com/paper/2610.02941/) (2026)

## Abstract (arXiv)

We present a novel online end-to-end neural diarization system, BW-EDA-EEND, that processes data incrementally for a variable number of speakers. The system is based on the Encoder-Decoder-Attractor (EDA) architecture of Horiguchi et al., but utilizes the incremental Transformer encoder, attending only to its left contexts and using block-level recurrence in the hidden states to carry information from block to block, making the algorithm complexity linear in time. We propose two variants: For unlimited-latency BW-EDA-EEND, which processes inputs in linear time, we show only moderate degradation for up to two speakers using a context size of 10 seconds compared to offline EDA-EEND. With more than two speakers, the accuracy gap between online and offline grows, but the algorithm still outperforms a baseline offline clustering diarization system for one to four speakers with unlimited context size, and shows comparable accuracy with context size of 10 seconds. For limited-latency BW-EDA-EEND, which produces diarization outputs block-by-block as audio arrives, we show accuracy comparable to the offline clustering-based system.