Researchers at John Hopkins University claim they’ve created a new method of pitch correction that’s “more than just Auto-Tune on steroids”, which uses AI to “enhance the naturalness and quality of pitch correction, surpassing previous tools.”
The new tool is called DiffPitcher and analyses the spectrogram of vocals that need to be corrected. It then identifies target notes, predicts the necessary adjustments and transforms that corrected spectrogram into audio. By contrast, traditional pitch correction software is trained on pairs of corrected and original vocals.
“Diff-Pitcher is a generative deep neural network that takes pitch correction technology to a new level. Its precision and control can not only help musical artists and producers but also open new possibilities in areas such as voice rehabilitation and assistive technologies,” says team member Jiarui Hai, a PhD student in the Whiting School of Engineering’s electrical and computer engineering department.
“[The results sound] really natural,” says Hai, “and unlike in older ways of fixing pitch, we can still regulate how high or low the voice goes.”
The new technology was presented at the 2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics last year. Researchers have also said could been used for applications other than music.
“The technology could revolutionise treatment for a spectrum of speech-related disorders, offering valuable support for post-laryngectomy patients and contributing to the voice rehabilitation of stroke victims,” says Hai.
In other AI-related news, a new AI-powered app Maverick SoundZ has been released. It bills itself as a new “all-in-one” virtual music manager, designed to help artists from all backgrounds get their music out there.
The app is priced at £7.99 per month and, according to the company, does all the jobs of a music management team. This includes a customised “battleplan” to guide artists through their careers, and even a database of radio stations, DJs, and journalists to aid promotion. Artists can also send their own press releases directly from the app.
Additionally, it also offers mental health check-ins, a calendar with a reminders feature, an AI-powered artist bio generator, press release generator, a caption generator for social media content, plus email templates.
The post Researchers claim to have invented a better version of Auto-Tune that uses AI appeared first on MusicTech.