# Domain-Aware Speaker Diarization On African-Accented English

arXiv: https://arxiv.org/abs/2509.21554 · HTML: https://mlsanity.com/paper/2509.21554/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 18 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 8 of 8)

- [A Review of Speaker Diarization: Recent Advances with Deep Learning](https://mlsanity.com/paper/2101.09624/) (2021)
- [CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking](https://mlsanity.com/paper/2303.00332/) (2023)
- [End-to-End Neural Speaker Diarization with Permutation-Free Objectives](https://mlsanity.com/paper/1909.05952/) (2019)
- [Fully Supervised Speaker Diarization](https://mlsanity.com/paper/1810.04719/) (2018)
- [AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR](https://mlsanity.com/paper/2310.00274/) (2023)
- [Speaker Diarization with Region Proposal Network](https://mlsanity.com/paper/2002.06220/) (2020)
- [Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond](https://mlsanity.com/paper/2502.03945/) (2025)
- [Reverb: Open-Source ASR and Diarization from Rev](https://mlsanity.com/paper/2410.03930/) (2024)

## Built on by (most cited first, 2 of 2)

- [Can large audio language models understand child stuttering speech? speech summarization, and source separation](https://mlsanity.com/paper/2510.20850/) (2025)
- [Reasoning Beyond Transcription: Audio Language Models on Child Stuttering Speech](https://mlsanity.com/paper/2609.07968/) (2026)

## Abstract (arXiv)

This study examines domain effects in speaker diarization for African-accented English. We evaluate multiple production and open systems on general and clinical dialogues under a strict DER protocol that scores overlap. A consistent domain penalty appears for clinical speech and remains significant across models. Error analysis attributes much of this penalty to false alarms and missed detections, aligning with short turns and frequent overlap. We test lightweight domain adaptation by fine-tuning a segmentation module on accent-matched data; it reduces error but does not eliminate the gap. Our contributions include a controlled benchmark across domains, a concise approach to error decomposition and conversation-level profiling, and an adaptation recipe that is easy to reproduce. Results point to overlap-aware segmentation and balanced clinical resources as practical next steps.