The GTM-UVIGO System for Audiovisual Diarization.

Eduardo Ramos-Muguerza Laura Docío Fernández José Luis Alba-Castro

Published in: IberSPEECH (2018)

Keyphrases

semi supervised
generative topographic mapping
multimedia content
audio visual
video retrieval
visual information
emotion recognition
speaker diarization
multimedia content analysis
preprocessing
metadata
self organizing maps
video clips
em algorithm
supervised learning
probabilistic model
video sequences
data sets