VisemeNet: Audio-Driven Animator-Centric Speech Animation.
Yang ZhouShan XuChris LandrethEvangelos KalogerakisSubhransu MajiKaran SinghPublished in: CoRR (2018)
Keyphrases
- audio stream
- audio visual
- audio signals
- broadcast news
- speaker identification
- emotion recognition
- cepstral features
- text to speech
- speech recognition
- audio features
- digital audio
- speech processing
- prosodic features
- linear predictive coding
- multimedia
- speech synthesis
- data driven
- acoustic signals
- audio video
- acoustic features
- audio recordings
- automatic transcription
- facial animation
- speech music discrimination
- computer graphics
- multi stream
- image processing
- spoken documents
- voice activity detection
- spoken language
- visual information
- speech signal
- digital video
- audio signal
- low level
- signal processing
- affect sensing
- video streams
- motion capture
- user centric
- human language
- virtual humans
- dialogue system
- audio files
- noisy environments
- computer animation
- speaker verification
- user interface
- computer vision