Accès ouvert · CC BY

DNCASR: End-to-End Training for Speaker-Attributed ASR

Article scientifique 2025 Sciences mathématiques et statistiques Anglais

Résumé

This paper introduces DNCASR, a novel endto-end trainable system designed for joint neural speaker clustering and automatic speech recognition (ASR), enabling speaker-attributed transcription of long multi-party meetings.DNCASR uses two separate encoders to independently encode global speaker characteristics and local waveform information, along with two linked decoders to generate speaker-attributed transcriptions.The use of linked decoders allows the entire system to be jointly trained under a unified loss function.By employing a serialised training approach, DNCASR effectively addresses overlapping speech in real-world meetings, where the link improves the prediction of speaker indices in overlapping segments.Experiments on the AMI-MDM meeting corpus demonstrate that the jointly trained DNCASR outperforms a parallel system that does not have links between the speaker and ASR decoders.Using cpWER to measure the speaker-attributed word error rate, DNCASR achieves a 9.0% relative reduction on the AMI-MDM Eval set.

Citer ce document

Zheng, X., Zhang, C., & Woodland, P. C. (2025). DNCASR: End-to-End Training for Speaker-Attributed ASR. https://doi.org/10.18653/v1/2025.acl-long.899

Exporter : BibTeX · RIS (Zotero, Mendeley, EndNote)

Accès au document

Texte intégral archivé sur SPHAERO, en accès ouvert : lisible gratuitement en ligne après connexion. Le document reste aussi disponible à sa source. Se connecter

Voir l'article sur le site de la revue

Licence et provenance

Licence : CC BY

Notice moissonnée depuis OpenAlex le 28/09/2026. Le document reste hébergé par sa source.
Voir le document à la source →

Statistiques

Consultations (hors robots) : 9

Téléchargements (hors robots) : 0

Méthode de comptage