Deep Learning for Asphyxiated Infant Cry Classification Based on Acoustic Features and Weighted Prosodic Features.
Chunyan JiXueli XiaoSunitha BasodiYi PanPublished in: iThings/GreenCom/CPSCom/SmartData (2019)
Keyphrases
- acoustic features
- speaker verification
- deep learning
- unsupervised learning
- noisy environments
- music information retrieval
- pattern recognition
- classification accuracy
- speech signal
- machine learning
- audio visual
- feature extraction
- visual features
- text classification
- support vector
- automatic speech recognition
- supervised learning
- emotion recognition
- feature vectors
- training set
- feature space