Speaker-Independent Speech-Driven Visual Speech Synthesis using Domain-Adapted Acoustic Models.
Ahmed Hussen AbdelazizBarry-John TheobaldJustin BinderGabriele FanelliPaul DixonNicholas ApostoloffThibaut WeiseSachin KajarekerPublished in: ICMI (2019)
Keyphrases
- speech recognition
- speech synthesis
- speaker independent
- acoustic models
- speaker dependent
- speech recognizer
- vocal tract
- automatic speech recognition
- hidden markov models
- language model
- speech signal
- pattern recognition
- speaker identification
- speech recognition systems
- noisy environments
- speaker recognition
- visual information
- low level
- bayesian networks
- multi modal