Promoting Independence of Depression and Speaker Features for Speaker Disentanglement in Speech-Based Depression Detection.
Lishi ZuoMan-Wai MakYouzhi TuPublished in: ICASSP (2024)
Keyphrases
- speech recognition
- speaker recognition
- automatic speech recognition
- speaker verification
- audio visual
- speaker identification
- mel frequency cepstral coefficients
- false positives
- speaker diarization
- speaker dependent
- feature extraction
- prosodic features
- synthesized speech
- low level
- noisy environments
- acoustic features
- feature space
- detection method
- speech signal
- automatic speech recognition systems
- feature vectors
- speech segments
- image features
- speech recognition systems
- anomaly detection
- vocal tract
- visual speech
- feature set
- speech recognizer
- adaboost classifier
- hidden markov models
- speech synthesis
- speech sounds
- gaussian mixture model
- audio features