Multi-view Temporal Alignment for Non-parallel Articulatory-to-Acoustic Speech Synthesis.
José Andrés González LópezMiriam Gonzalez-AtienzaAlejandro Gómez AlanísJosé Luis Pérez-CórdobaPhil D. GreenPublished in: CoRR (2020)
Keyphrases
- multi view
- speech synthesis
- prosodic features
- vocal tract
- speech recognition
- single view
- text to speech
- multiple views
- d objects
- camera calibration
- multiple cameras
- three dimensional
- depth map
- scene reconstruction
- automatic speech recognition
- multi view stereo
- semi supervised
- viewpoint
- multiple viewpoints
- language model
- multi view images
- co training
- visual hull
- multi view learning
- acoustic features
- multi view clustering
- view synthesis
- range images
- active learning
- pattern recognition
- training data