SERAPHIM - A Wavetable Synthesis System with 3D Lip Animation for Real-time Speech and Singing Applications on Mobile Platforms

Authors: 
Paul Chan Yaozhu, Dong Ming Hui, Li Haizhou
Publication: 
INTERSPEECH - HLT TOP CONFERENCE
Publication Date: 
8 Sep 2016
Strategic Thrust: 
Media, Intelligence
Abstract: 
1) This paper is on a novel real-time singing synthesis technique that addresses issues unsolved by current competitors.2) State-of-the-art real-time singing synthesis systems employ static methods that either are only real-time to the syllable level or are restricted to vowels. Our solution employ a dynamic method that is real-time to the frame level and are not restricted to vowels.3) dynamic system for real-time singing synthesis4) outstanding deployability, but main advantage is in the performance: it's the only system that is real-time to the frame level and are not restricted to vowels.5) this is the pioneering dynamic method for singing synthesis system