Login / Signup
Combining CNN and BLSTM to Extract Textual and Acoustic Features for Recognizing Stances in Mandarin Ideological Debate Competition.
Linchuan Li
Zhiyong Wu
Mingxing Xu
Helen M. Meng
Lianhong Cai
Published in:
INTERSPEECH (2016)
Keyphrases
</>
acoustic features
music genre classification
music information retrieval
speaker verification
speech signal
automatic speech recognition
visual features
image processing
speech recognition
emotion recognition
image retrieval
template matching
broadcast news