Reducing footprint of unit selection based text-to-speech system using compressed sensing and sparse representation.
Pulkit SharmaVinayak Abrol NiveditaAnil Kumar SaoPublished in: Comput. Speech Lang. (2018)
Keyphrases
- compressed sensing
- sparse representation
- text to speech
- image reconstruction
- dictionary learning
- random projections
- sparse coding
- image patches
- face recognition
- signal processing
- image classification
- word processing
- natural images
- image representation
- dimensionality reduction
- high dimensional data
- compressive sensing
- signal recovery
- orthogonal matching pursuit
- machine learning
- object recognition
- feature selection
- computer vision