Implementing Acoustic-Prosodic Entrainment in a Conversational Avatar.
Rivka LevitanStefan BenusRamiro H. GálvezAgustín GravanoFlorencia SavorettiMarián TrnkaAndreas WeiseJulia HirschbergPublished in: INTERSPEECH (2016)
Keyphrases
- prosodic features
- virtual world
- multi modal
- speech recognition
- virtual reality
- cooperative
- human computer interaction
- spoken language
- conversational agent
- text to speech
- source localization
- text to speech synthesis
- real time
- bird species
- underwater acoustic
- speech synthesis
- speaker verification
- hidden markov models
- artificial neural networks
- natural language
- video sequences
- website
- feature selection