# Speaker Diarization as a Fully Online Learning Problem in MiniVox

arXiv: https://arxiv.org/abs/2006.04376 · HTML: https://mlsanity.com/paper/2006.04376/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2020.

## Built on by (most cited first, 7 of 7)

- [Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook](https://mlsanity.com/paper/2210.13623/) (2022)
- [SupervisorBot: NLP-Annotated Real-Time Recommendations of Psychotherapy Treatment Strategies with Deep Reinforcement Learning](https://mlsanity.com/paper/2208.13077/) (2022)
- [Psychotherapy AI Companion with Reinforcement Learning Recommendations and Interpretable Policy Dynamics](https://mlsanity.com/paper/2303.09601/) (2023)
- [Optimal Epidemic Control as a Contextual Combinatorial Bandit with Budget](https://mlsanity.com/paper/2106.15808/) (2021)
- [Evolutionary Multi-Armed Bandits with Genetic Thompson Sampling](https://mlsanity.com/paper/2205.10113/) (2022)
- [A Reinforcement Learning Framework for Online Speaker Diarization](https://mlsanity.com/paper/2302.10924/) (2023)
- [A Review of Common Online Speaker Diarization Methods](https://mlsanity.com/paper/2406.14464/) (2024)

## Abstract (arXiv)

We proposed a novel machine learning framework to conduct real-time multi-speaker diarization and recognition without prior registration and pretraining in a fully online learning setting. Our contributions are two-fold. First, we proposed a new benchmark to evaluate the rarely studied fully online speaker diarization problem. We built upon existing datasets of real world utterances to automatically curate MiniVox, an experimental environment which generates infinite configurations of continuous multi-speaker speech stream. Second, we considered the practical problem of online learning with episodically revealed rewards and introduced a solution based on semi-supervised and self-supervised learning methods. Additionally, we provided a workable web-based recognition system which interactively handles the cold start problem of new user's addition by transferring representations of old arms to new ones with an extendable contextual bandit. We demonstrated that our proposed method obtained robust performance in the online MiniVox framework.