Deep complementary features for speaker identification in TV broadcast data - researchr publication related

researchr

You are not signed in
Sign in
Sign up

Mateusz Budnik, Ali Khodabakhsh, Laurent Besacier, Cenk Demiroglu. Deep complementary features for speaker identification in TV broadcast data. In Luis Javier Rodríguez-Fuentes, Eduardo Lleida, editors, Odyssey 2016: The Speaker and Language Recognition Workshop, Bilbao, Spain, June 21-24, 2016. pages 146-151, ISCA, 2016. [doi]

The following publications are possibly variants of this publication:

Unsupervised Speaker Identification in TV Broadcast Based on Written NamesJohann Poignant, Laurent Besacier, Georges Quénot. taslp, 23(1):57-68, 2015. [doi]

Unsupervised Speaker Identification using Overlaid Texts in TV BroadcastJohann Poignant, Hervé Bredin, Viet Bac Le, Laurent Besacier, Claude Barras, Georges Quénot. interspeech 2012: 2650-2653 [doi]

runs on WebDSL