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...
שמור ב:
| Principais autores: | , |
|---|---|
| פורמט: | Artigo |
| שפה: | Inglês |
| יצא לאור: |
SpringerOpen
2025-11-01
|
| סדרה: | EURASIP Journal on Audio, Speech, and Music Processing |
| נושאים: | |
| גישה מקוונת: | https://doi.org/10.1186/s13636-025-00431-4 |
| תגים: |
אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!
|
