15th Annual Conference of the International Speech Communication Association

September 14-18, 2014

I2R Speech2Singing Perfects Everyone's Singing

Minghui Dong, S. W. Lee, Haizhou Li, Paul Chan, Xuejian Peng, Jochen Walter Ehnes, Dongyan Huang

A*STAR, Singapore

High-quality natural singing is appealing to everyone. However, singing well is not trivial. Professional singers are trained and practised over the years for various singing skills, such as sense of rhythm, precision in pitch, vocal control and personal styling etc. We, Institute for Infocomm Research (I2R), in Singapore has developed a personalized, real-time singing synthesis technology for the general public. Given an input singing (maybe in mediocre to poor quality), our technology will convert it into a nice piece of singing, perfecting it with correct rhythm and fundamental frequency over the time. Now, you can simply read the lyrics, record in our mobile apps and generate a pleasant and personalized singing with your own vocal characteristics.

Full Paper

Bibliographic reference.  Dong, Minghui / Lee, S. W. / Li, Haizhou / Chan, Paul / Peng, Xuejian / Ehnes, Jochen Walter / Huang, Dongyan (2014): "I2r speech2singing perfects everyone's singing", In INTERSPEECH-2014, 2148-2149.