Creating Personalized Synthetic Voices from Articulation Impaired Speech Using Augmented Reconstruction Loss.
Yusheng TianJingyu LiTan LeePublished in: CoRR (2024)
Keyphrases
- three dimensional
- speech recognition
- speech signal
- image reconstruction
- reconstruction process
- high resolution
- adaptive learning
- e learning
- endpoint detection
- speech synthesis
- text to speech
- personalized recommendation
- user profiles
- real world
- reconstruction method
- compressive sensing
- individual user
- compressed sensing
- real images are presented
- d objects
- multi modal
- speaker recognition
- spoken dialogue systems
- tomographic reconstruction
- user oriented
- context aware
- audio visual
- surface model
- human computer interaction
- noisy environments
- automatic speech recognition
- reconstruction error
- information services