Speaker Change Detection in Broadcast TV Using Bidirectional Long Short-Term Memory Networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Speaker Change Detection in Broadcast TV Using Bidirectional Long Short-Term Memory Networks

Résumé

Speaker change detection is an important step in a speaker di-arization system. It aims at finding speaker change points in the audio stream. In this paper, it is treated as a sequence labeling task and addressed by Bidirectional long short term memory networks (Bi-LSTM). The system is trained and evaluated on the Broadcast TV subset from ETAPE database. The result shows that the proposed model brings good improvement over conventional methods based on BIC and Gaussian Divergence. For instance, in comparison to Gaussian divergence, it produces speech turns that are 19.5% longer on average, with the same level of purity.
Fichier principal
Vignette du fichier
0065.PDF (316.4 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01690244 , version 1 (23-01-2018)

Identifiants

Citer

Ruiqing Yin, Hervé Bredin, Claude Barras. Speaker Change Detection in Broadcast TV Using Bidirectional Long Short-Term Memory Networks. Interspeech 2017, Aug 2017, Stockholm, Sweden. ⟨10.21437/Interspeech.2017-65⟩. ⟨hal-01690244⟩
902 Consultations
2767 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More