Multi-Channel Sequence-to-Sequence Neural Diarization: Experimental Results for The MISP 2025 Challenge
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912387145138176 |
|---|---|
| author | Cheng, Ming Su, Fei Li, Cancan Liu, Juan Li, Ming |
| author_facet | Cheng, Ming Su, Fei Li, Cancan Liu, Juan Li, Ming |
| contents | This paper describes the speaker diarization system developed for the Multimodal Information-Based Speech Processing (MISP) 2025 Challenge. First, we utilize the Sequence-to-Sequence Neural Diarization (S2SND) framework to generate initial predictions using single-channel audio. Then, we extend the original S2SND framework to create a new version, Multi-Channel Sequence-to-Sequence Neural Diarization (MC-S2SND), which refines the initial results using multi-channel audio. The final system achieves a diarization error rate (DER) of 8.09% on the evaluation set of the competition database, ranking first place in the speaker diarization task of the MISP 2025 Challenge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_16387 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Channel Sequence-to-Sequence Neural Diarization: Experimental Results for The MISP 2025 Challenge Cheng, Ming Su, Fei Li, Cancan Liu, Juan Li, Ming Audio and Speech Processing This paper describes the speaker diarization system developed for the Multimodal Information-Based Speech Processing (MISP) 2025 Challenge. First, we utilize the Sequence-to-Sequence Neural Diarization (S2SND) framework to generate initial predictions using single-channel audio. Then, we extend the original S2SND framework to create a new version, Multi-Channel Sequence-to-Sequence Neural Diarization (MC-S2SND), which refines the initial results using multi-channel audio. The final system achieves a diarization error rate (DER) of 8.09% on the evaluation set of the competition database, ranking first place in the speaker diarization task of the MISP 2025 Challenge. |
| title | Multi-Channel Sequence-to-Sequence Neural Diarization: Experimental Results for The MISP 2025 Challenge |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.16387 |