# Chronological Self-Training for Real-Time Speaker Diarization

arXiv: https://arxiv.org/abs/2208.03393 · HTML: https://mlsanity.com/paper/2208.03393/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 5 Aug 2022.

## Builds on (most cited first, 6 of 6)

- [Generalized End-to-End Loss for Speaker Verification](https://mlsanity.com/paper/1710.10467/) (2017)
- [End-to-End Neural Speaker Diarization with Permutation-Free Objectives](https://mlsanity.com/paper/1909.05952/) (2019)
- [Speaker Diarization with LSTM](https://mlsanity.com/paper/1710.10468/) (2017)
- [Fully Supervised Speaker Diarization](https://mlsanity.com/paper/1810.04719/) (2018)
- [Links: A High-Dimensional Online Clustering Method](https://mlsanity.com/paper/1801.10123/) (2018)
- [Deep Self-Supervised Hierarchical Clustering for Speaker Diarization](https://mlsanity.com/paper/2008.03960/) (2020)

## Abstract (arXiv)

Diarization partitions an audio stream into segments based on the voices of the speakers. Real-time diarization systems that include an enrollment step should limit enrollment training samples to reduce user interaction time. Although training on a small number of samples yields poor performance, we show that the accuracy can be improved dramatically using a chronological self-training approach. We studied the tradeoff between training time and classification performance and found that 1 second is sufficient to reach over 95% accuracy. We evaluated on 700 audio conversation files of about 10 minutes each from 6 different languages and demonstrated average diarization error rates as low as 10%.