Acoustic features of multimodal prominences: Do visual beat gestures affect verbal pitch accent realization?
Gilbert AmbrazaitisDavid HousePublished in: AVSP (2017)
Keyphrases
- acoustic features
- visual features
- visual speech
- automatic speech recognition
- speech recognition
- music genre classification
- speech signal
- hidden markov models
- visual information
- speaker verification
- music information retrieval
- image classification
- audio features
- audio visual
- low level
- visual data
- multi modal
- cross correlation
- pointing gestures
- broadcast news
- image retrieval
- keywords
- neural network