Analyzing Input and Output Representations for Speech-Driven Gesture Generation.
Taras KucherenkoDai HasegawaGustav Eje HenterNaoshi KanekoHedvig KjellströmPublished in: IVA (2019)
Keyphrases
- input data
- desired output
- multiple output
- multimodal interfaces
- input variables
- hidden units
- speech recognition
- text input
- gesture recognition
- neural network
- hidden markov models
- hand movements
- speech signal
- feedback loop
- dialogue system
- multi stream
- data sets
- sign language
- hand gestures
- pattern recognition
- input device
- rbf network
- input pattern
- input patterns
- speaker recognition
- text to speech
- audio visual
- variable selection
- speech synthesis
- human computer interaction
- data driven
- gaze control