Visemenet: audio-driven animator-centric speech animation.
Yang ZhouZhan XuChris LandrethEvangelos KalogerakisSubhransu MajiKaran SinghPublished in: ACM Trans. Graph. (2018)
Keyphrases
- audio stream
- audio visual
- broadcast news
- audio signals
- text to speech
- speaker identification
- cepstral features
- digital audio
- emotion recognition
- prosodic features
- audio features
- linear predictive coding
- speech music discrimination
- speech recognition
- audio recordings
- speech processing
- multi modal
- multi stream
- data driven
- speech synthesis
- automatic transcription
- speaker verification
- audio video
- acoustic signals
- multimedia
- speech signal
- visual information
- automatic speech recognition
- user centric
- facial animation
- computer graphics
- signal processing
- speech recognition technology
- hidden markov models
- acoustic features
- gaussian mixture model
- feature extraction
- digital video
- speaker diarization
- motion capture
- visual speech
- spoken documents
- user interface
- pattern recognition