Sound source separation for robot audition using deep learning.

Kuniaki Noda Naoya Hashimoto Kazuhiro Nakadai Tetsuya Ogata

Published in: Humanoids (2015)

Keyphrases

deep learning
source separation
blind source separation
independent component analysis
unsupervised learning
denoising
machine learning
single channel
mental models
temporal structure
weakly supervised
image processing
data sets
sound source
audio features