Tracking depression severity from audio and video based on speech articulatory coordination.
James R. WilliamsonDiana YoungAndrew A. NierenbergJames NiemiBrian S. HelferThomas F. QuatieriPublished in: Comput. Speech Lang. (2019)
Keyphrases
- multi stream
- audio visual speech recognition
- speech recognition
- audio visual
- vocal tract
- speech signal
- acoustic features
- speaker identification
- audio stream
- speech synthesis
- text to speech
- broadcast news
- audio features
- speech processing
- audio signals
- automatic speech recognition
- digital audio
- real time
- emotion recognition
- multimedia
- particle filter
- cepstral features
- visual information
- cooperative
- prosodic features
- multi agent systems
- hidden markov models
- object tracking
- audio recordings
- moving target
- visual tracking
- linear predictive coding
- acoustic signals
- spontaneous speech
- noisy environments
- multiagent systems
- speaker recognition
- music information retrieval
- video streams
- signal processing
- multi modal
- motion model
- pattern recognition