Multimodal exemplar-based voice conversion using lip features in noisy environments.

Kenta Masaka Ryo Aihara Tetsuya Takiguchi Yasuo Ariki

Published in: INTERSPEECH (2014)

Keyphrases

noisy environments
feature extraction
feature space
speech recognition
visual speech
voice activity detection
machine learning
computer vision
image processing
feature vectors
feature set
noise reduction
background noise
digit recognition
feature transformation
speech enhancement