A multimodal approach to extract optimized audio features for speaker detection.

Patricia Besson Murat Kunt Torsten Butz Jean-Philippe Thiran

Published in: EUSIPCO (2005)

Keyphrases

audio visual
audio features
multi modal
visual information
acoustic features
speaker verification
speaker identification
music retrieval
visual data
multimedia
sound source
music recommendation
metadata
pattern recognition
feature set
speech recognition