VocaliD, Inc., a speech technology company that creates personalized digital voices for those living with voicelessness, has launched its online BeSpoke voice studio. The announcement was made at the Biennial Conference of the International Society for Augmentative and Alternative Communication (ISAAC) in Toronto.
Supported by the National Science Foundation and the National Institutes of Health, VocaliD’s innovation is based on a discovery by Founder and CEO Dr. Rupal Patel and her colleagues that even a single vowel contains enough “vocal DNA” to seed the voice personalization process.
The BeSpoke process captures a recipient’s unique vocal identity and blends it with recordings from a healthy speaker — matched by gender, age and accent — within the company’s voice bank of 14,000+-plus contributors. This blended voice is then used in the recipient’s electronic communications device — creating a BeSpoke voice.
“The inspiration for VocaliD came when I saw a young girl and older man communicating using their assistive devices, but with the exact same adult male voice,” said Dr. Patel, a professor at Northeastern University. “We wouldn’t dream of fitting a little girl with the prosthetic limb of a grown man, so why then the same prosthetic voice?”
More than ten million globally are unable to speak and rely on assistive devices with a limited selection of generic, synthetic voices. VocaliD’s vision is to provide affordable, personalized and natural-sounding voices for the voiceless.
The company is also exploring similar personalization for the rapidly increasing number of everyday devices currently narrated by generic voices.