Pitch-Perfect Vocals

Spring 2024

illustration of a robot singing in a recording booth
(illustration created by DALL·E 3)

Once a solution for amateur, off-key singers on karaoke nights, Auto-Tune and other voice tuning software have progressed from the club to the recording industry but never beyond sounding artificial.

Now, Whiting School researchers have made significant improvements to traditional voice tuning software’s previous capabilities. This innovation—called Diff-Pitcher—seamlessly corrects out-of-tune singing while maintaining the original vocal timbre and naturalness, expanding its possible applications beyond entertainment and the music industry and into the health care setting.

“Diff-Pitcher is a generative deep neural network that takes pitch-correction technology to a new level. Its precision and control not only help musical artists and producers but also open new possibilities in voice rehabilitation and assistive technologies,” says team member Jiarui Hai, a PhD student in the Department of Electrical and Computer Engineering, who worked on the project with lead researcher Mounya Elhilali, a professor in electrical and computer engineering.

“[The results sound] really natural, and unlike in older ways of fixing pitch, we can still regulate how high or low the voice goes,” Hai says. “The technolog y could revolutionize treatment for a spectrum of speech-related disorders, offering valuable support for post-lar yngectomy patients and contributing to the voice rehabilitation of stroke victims.”

In Impact