Audio-visual voice conversion using noise-robust features.

Kohei Sawada Masanori Takehara Satoshi Tamura Satoru Hayamizu

Published in: ICASSP (2014)

Keyphrases

audio visual
person authentication
emotion recognition
multi modal
audio features
co occurrence
multimedia
feature vectors
noisy environments
multimodal fusion
noise reduction
low level
feature space
visual information
data management
feature set
feature extraction