Detecting Multiple Disfluencies from Speech using Pre-linguistic Automatic Syllabification with Acoustic and Prosody Features.
Utkarsh MehrotraSparsh GargKrishna GurugubelliAnil Kumar VuppalaPublished in: APSIPA ASC (2021)
Keyphrases
- low level
- emotional speech
- audio visual
- rich set
- speech recognition
- speech recognition systems
- feature extraction
- text to speech
- spontaneous speech
- automatic speech recognition
- feature set
- co occurrence
- feature vectors
- lexical features
- semi automatic
- fully automatic
- natural language processing
- speech synthesis
- prosodic features
- speech segments
- linguistic knowledge
- emotion recognition
- human computer interaction
- multi modal
- classification accuracy
- feature space
- pattern recognition