Exploiting the speech-gesture link to capture fine-grained prosodic prominence impressions and listening strategies.
Petra WagnerAleksandra CwiekBarbara SamlowskiPublished in: J. Phonetics (2019)
Keyphrases
- fine grained
- synthesized speech
- speech recognition
- coarse grained
- multimodal interfaces
- text to speech synthesis
- text to speech
- speech synthesis
- hidden markov models
- prosodic features
- access control
- tightly coupled
- gesture recognition
- hand movements
- massively parallel
- human computer interaction
- databases
- spoken language
- speaker verification