Domain-Aware Speaker Diarization On African-Accented English
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911176533737472 |
|---|---|
| author | Okocha, Chibuzor Ezema, Kelechi Grant, Christan |
| author_facet | Okocha, Chibuzor Ezema, Kelechi Grant, Christan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21554 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Domain-Aware Speaker Diarization On African-Accented English Okocha, Chibuzor Ezema, Kelechi Grant, Christan Computation and Language Artificial Intelligence Machine Learning 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. |
| title | Domain-Aware Speaker Diarization On African-Accented English |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2509.21554 |