Style Transfer for Co-speech Gesture Animation: A Multi-speaker Conditional-Mixture Approach.
Chaitanya AhujaDong Won LeeYukiko I. NakanoLouis-Philippe MorencyPublished in: ECCV (18) (2020)
Keyphrases
- speech recognition
- speaker recognition
- audio visual
- automatic speech recognition
- speaker identification
- speaker verification
- multimodal interfaces
- gaussian mixture model
- hidden markov models
- speech signal
- speaker dependent
- prosodic features
- broadcast news
- mixture model
- multi stream
- automatic speech recognition systems
- vocal tract
- speaker diarization
- user interface
- speech synthesis
- hand movements
- speech recognizer
- acoustic features
- speech sounds
- automatic transcription
- gesture recognition
- knowledge transfer
- text to speech
- multi modal
- speech recognition systems
- acoustic models
- computer graphics
- transfer learning