Investigation of Speaker Group-Dependent Modelling for Recognition of Affective States from Speech.
Ingo SiegertDavid Philippou-HübnerKim HartmannRonald BöckAndreas WendemuthPublished in: Cogn. Comput. (2014)
Keyphrases
- affective states
- audio visual
- speech recognition
- automatic speech recognition systems
- affect recognition
- speech sounds
- speaker dependent
- automatic transcription
- speaker independent
- emotion recognition
- speaker verification
- speaker recognition
- speech signal
- automatic speech recognition
- speaker identification
- emotional state
- multi modal
- noisy environments
- intelligent tutoring systems
- visual speech
- feature extraction
- vocal tract
- visual information
- affect sensing
- hidden markov models
- mel frequency cepstral coefficients
- multimedia
- tutoring system
- speech synthesis
- action recognition
- log files
- broadcast news
- website
- image sequences
- visual features