Leveraging Speaker Embeddings in End-to-End Neural Diarization for Two-Speaker Scenarios
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911939208151040 |
|---|---|
| author | Alvarez-Trejos, Juan Ignacio Labrador, Beltrán Lozano-Diez, Alicia |
| author_facet | Alvarez-Trejos, Juan Ignacio Labrador, Beltrán Lozano-Diez, Alicia |
| contents | End-to-end neural speaker diarization systems are able to address the speaker diarization task while effectively handling speech overlap. This work explores the incorporation of speaker information embeddings into the end-to-end systems to enhance the speaker discriminative capabilities, while maintaining their overlap handling strengths. To achieve this, we propose several methods for incorporating these embeddings along the acoustic features. Furthermore, we delve into an analysis of the correct handling of silence frames, the window length for extracting speaker embeddings and the transformer encoder size. The effectiveness of our proposed approach is thoroughly evaluated on the CallHome dataset for the two-speaker diarization task, with results that demonstrate a significant reduction in diarization error rates achieving a relative improvement of a 10.78% compared to the baseline end-to-end model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_01317 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging Speaker Embeddings in End-to-End Neural Diarization for Two-Speaker Scenarios Alvarez-Trejos, Juan Ignacio Labrador, Beltrán Lozano-Diez, Alicia Sound Artificial Intelligence Audio and Speech Processing End-to-end neural speaker diarization systems are able to address the speaker diarization task while effectively handling speech overlap. This work explores the incorporation of speaker information embeddings into the end-to-end systems to enhance the speaker discriminative capabilities, while maintaining their overlap handling strengths. To achieve this, we propose several methods for incorporating these embeddings along the acoustic features. Furthermore, we delve into an analysis of the correct handling of silence frames, the window length for extracting speaker embeddings and the transformer encoder size. The effectiveness of our proposed approach is thoroughly evaluated on the CallHome dataset for the two-speaker diarization task, with results that demonstrate a significant reduction in diarization error rates achieving a relative improvement of a 10.78% compared to the baseline end-to-end model. |
| title | Leveraging Speaker Embeddings in End-to-End Neural Diarization for Two-Speaker Scenarios |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2407.01317 |