Speaker Identification Based on Integrated Face Direction in a Group Conversation.

Naoto Ienaga Yuko Ozasa Hideo Saito

Published in: WACV Workshops (2017)

Keyphrases

speaker identification
gaussian mixture model
speech recognition
speech signal
speaker recognition
noisy environments
feature extraction
broadcast news
face images
mixture model
natural language
language model
em algorithm
feature vectors
pattern recognition
bayesian networks
multimedia