Login / Signup
Speech-to-Gesture Generation: A Challenge in Deep Learning Approach with Bi-Directional LSTM.
Kenta Takeuchi
Dai Hasegawa
Shinichi Shirakawa
Naoshi Kaneko
Hiroshi Sakuta
Kazuhiko Sumi
Published in:
HAI (2017)
Keyphrases
</>
bi directional
deep learning
unsupervised learning
unsupervised feature learning
multimodal interfaces
machine learning
weakly supervised
associative memory
deep architectures
recurrent neural networks
mental models
computer vision
feature selection
face recognition
probabilistic model