Speaker diarization using data-driven audio sequencing.

Houssemeddine Khemiri Dijana Petrovska-Delacrétaz Gérard Chollet

Published in: ICASSP (2013)

Keyphrases

data driven
speaker diarization
audio stream
broadcast news
speaker identification
speech recognition
bayesian information criterion
multimedia
speaker verification
video search
image processing
video streams
learning algorithm
automatic speech recognition
audio visual
multi modal
feature vectors
face recognition