Combining Speaker Turn Embedding and Incremental Structure Prediction for Low-Latency Speaker Diarization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Combining Speaker Turn Embedding and Incremental Structure Prediction for Low-Latency Speaker Diarization

Résumé

Real-time speaker diarization has many potential applications, including public security, biometrics or forensics. It can also significantly speed up the indexing of increasingly large mul-timedia archives. In this paper, we address the issue of low-latency speaker diarization that consists in continuously detecting new or reoccurring speakers within an audio stream, and determining when each speaker is active with a low latency (e.g. every second). This is in contrast with most existing approaches in speaker diarization that rely on multiple passes over the complete audio recording. The proposed approach combines speaker turn neural embeddings with an incremental structure prediction approach inspired by state-of-the-art Natural Language Processing models for Part-of-Speech tagging and dependency parsing. It can therefore leverage both information describing the utterance and the inherent temporal structure of interactions between speakers to learn, in supervised framework , to identify speakers. Experiments on the Etape broadcast news benchmark validate the approach.
Fichier principal
Vignette du fichier
1067.PDF (555.05 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01690162 , version 1 (23-01-2018)

Identifiants

Citer

Guillaume Wisniewksi, Hervé Bredin, Grégory Gelly, Claude Barras. Combining Speaker Turn Embedding and Incremental Structure Prediction for Low-Latency Speaker Diarization. Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Aug 2017, Stockholm, Sweden. ⟨10.21437/Interspeech.2017-1067⟩. ⟨hal-01690162⟩
135 Consultations
183 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More