Speech Emotion Recognition using Threshold Fusion for Enhancing Audio Sensitivity.
Zhaojie LuoStefan ChristianssonBence LadóczkiKazunori KomataniPublished in: MMAsia (Workshops) (2023)
Keyphrases
- multimodal fusion
- emotion recognition
- audio visual
- multimodal interfaces
- information fusion
- emotional speech
- multi modal
- audio stream
- human computer interaction
- visual information
- multimodal interaction
- multimedia
- audio features
- text to speech
- audio signals
- emotional state
- broadcast news
- speaker verification
- multi stream
- text to speech synthesis
- speaker identification
- visual data
- data fusion
- speech signal
- high robustness
- emotion classification
- multi sensor
- sentiment analysis
- prosodic features
- sensitivity analysis
- facial expressions
- fusion method
- digital audio
- low level