ZS-MSTM: Zero-Shot Style Transfer for Gesture Animation driven by Text and Speech using Adversarial Disentanglement of Multimodal Style Encoding.
Mireille FaresCatherine PelachaudNicolas ObinPublished in: CoRR (2023)
Keyphrases
- multimodal interfaces
- authorship attribution
- multi stream
- text to speech
- multi modal
- database
- text to speech synthesis
- speech recognition
- computer graphics
- audio visual
- multimodal interaction
- english text
- automatic speech recognition
- lexical features
- natural language generation
- text retrieval
- text categorization
- text mining
- hidden markov models
- information retrieval