Exploring deep learning architectures for automatically grading non-native spontaneous speech.

Jidong Tao Shabnam Ghaffarzadegan Lei Chen Klaus Zechner

Published in: ICASSP (2016)

Keyphrases

deep learning
spontaneous speech
hand crafted
unsupervised learning
mental models
human machine interaction
spoken language
machine learning
weakly supervised
computer vision
multiscale
visual features
automatic speech recognition
spoken document retrieval