Speech Recognition and Synthesis

While computer vision and natural language processing give computers the ability to understand the world visually and understand language it is imperative that understanding is conveyed in the direction of computer to human. This is achieved by giving computers the ability to understand speech coming from external sources and synthesise its own speech in order to have useful discussions with a human being. ThinkGradient community will be researching and developing new techniques in this space to improve the current state of the art in speech recognition and synthesis.