Speaker embedding loss for end-to-end speaker diarization without external embedding networks
Abstract This paper introduces a novel speaker embedding loss function designed to improve the performance of end-to-end neural diarization (EEND) systems by enhancing speaker discrimination. Unlike previous methods that require additional speaker embedding networks or pre-training on large-scale sp...
Guardat en:
| Autors principals: | , |
|---|---|
| Format: | Artigo |
| Idioma: | Inglês |
| Publicat: |
SpringerOpen
2025-11-01
|
| Col·lecció: | EURASIP Journal on Audio, Speech, and Music Processing |
| Matèries: | |
| Accés en línia: | https://doi.org/10.1186/s13636-025-00431-4 |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|