TypeTalker: A Speech Synthesis-Based Multi-Modal Commenting System.
Ian ArawjoDongwook YoonFrançois GuimbretièrePublished in: CSCW (2017)
Keyphrases
- multi modal
- speech synthesis
- speech recognition
- text to speech
- prosodic features
- vocal tract
- audio visual
- cross modal
- multi modality
- high dimensional
- image annotation
- pattern recognition
- semantic concepts
- video search
- image processing
- machine learning
- fusing multiple
- uni modal
- humanoid robot
- hidden markov models
- metadata