The GTM-UVIGO System for Audiovisual Diarization 2020.

Manuel Porta-Lorenzo José Luis Alba-Castro Laura Docío Fernández

Published in: IberSPEECH (2021)

Keyphrases

semi supervised
visual information
audio visual
speaker diarization
multimedia content
generative topographic mapping
emotion recognition
neural network
machine learning
information retrieval
face recognition
maximum likelihood
mixture model
video retrieval