Creating Personalized Synthetic Voices from Articulation Impaired Speech Using Augmented Reconstruction Loss.
Yusheng TianJingyu LiTan LeePublished in: ICASSP (2024)
Keyphrases
- e learning
- speech recognition
- personalized search
- compressed sensing
- user profiles
- discrete tomography
- high resolution
- reconstruction process
- real images are presented
- adaptive learning
- speech signal
- audio visual
- image reconstruction
- three dimensional
- reconstructed image
- website
- recognition engine
- compressive sensing
- user oriented
- discrete sets
- real world
- tomographic reconstruction
- personalized information
- linear prediction
- emotion recognition
- dialogue system
- user modeling
- error rate
- image quality