File(s) under permanent embargo
Combination of CNN and RNN for speech emotion recognition
conference contribution
posted on 2023-05-23, 15:16 authored by Vo, TH, Soonja YeomSoonja Yeom, Na, IS, Oh, A, Lee, GS, Yang, HJ, Kim, SHSpeech Emotion Recognition has several potential applications in health care and human-computer interaction. In recent years, some studies use deep learning to deal with this task, but most of them use shallow neural networks due to the overfitting problem. We proposed an architecture that combines CNN and RNN to learn not only to capture the spatial but also the time-series information. The experiments on VGG-16 and ResNet-101 like networks gave a compatible result with some recent studies.
History
Publication title
SMA2019 - The International Conference on Smart Media & ApplicationsPagination
163 -166ISSN
2287-4348Department/School
School of Information and Communication TechnologyPublisher
Smart Media - Korean Institute of Smart MediaPlace of publication
South KoreaEvent title
SMA 2019: The 8th International Conference on Smart Media and ApplicationsEvent Venue
Hilton Guam Resort & Spa, GUAMDate of Event (Start Date)
2019-12-05Date of Event (End Date)
2019-12-07Rights statement
Copyright unknownRepository Status
- Restricted