Effects of feature type, learning algorithm and speaking style for depression detection from speech.
Vikramjit MitraElizabeth ShribergPublished in: ICASSP (2015)
Keyphrases
- learning algorithm
- detection accuracy
- automatic detection
- detection rate
- object detection
- detection method
- image features
- detection algorithm
- learning rate
- adaboost classifier
- supervised learning
- back propagation
- speech recognition
- learning problems
- machine learning
- learning scheme
- text to speech
- noisy environments
- endpoint detection
- voice activity detection
- false alarms
- generalization error
- hough transform
- false positives
- active learning
- learning process
- feature vectors