MFCC-based deep convolutional neural network for audio depression recognition.
Yafan WangXiaoyong LuDaimin ShiPublished in: IALP (2022)
Keyphrases
- convolutional neural network
- face detection
- feature extraction
- multimedia
- recognition rate
- speaker identification
- audio signals
- neural network
- multi modal
- object detection
- audio video
- pairwise
- audio recordings
- audio visual
- emotion recognition
- audio features
- mel frequency cepstral coefficients
- recognition accuracy
- broadcast news
- visual data
- speech recognition
- signal processing
- image processing
- feature selection