VocaliD: Custom-Made Voices for People Unable to Speak
Innovator: Rupal Patel
Founder and president of VocaliD, a synthetic-voice startup with three full-time employees in Belmont, Mass.
Form and function
For people rendered unable to speak by cerebral palsy, stroke, or traumatic brain injury, VocaliD’s software creates custom speech patterns that sound like the original person’s voice.
Patel, a speech pathology and computer science professor at Northeastern, began developing her software after meeting a little girl and a grown man who spoke in the same flat, computer-assisted voice.
After recording whatever sounds a person can produce, VocaliD’s software sifts through its database of 15,000 volunteers’ voice samples for the closest match, based on factors like age and accent.
The software blends the subject’s sample with the surrogate voice’s thousands of prerecorded sentences to turn typed text into speech.
VocaliD has received $365,000 from the National Science Foundation and the National Institutes of Health, plus $128,000 on Indiegogo.
VocaliD’s standard price is $1,250, plus $240 a year for updates.
About 500,000 Americans who use computer assistance to speak could make use of VocaliD, says Patel.
The first seven of VocaliD’s initial 60 subjects received their custom voices in December, and the software is slated for wider release online by yearend. Patel is seeking $1 million to further automate the voice-building process. “Cost and whether insurance is going to cover it will be the big thing,” says Lisa Schoenbrodt, who chairs the speech science department at Loyola University Maryland. Patel says she’s working on bringing the price down to below $1,000, and on pitches to robotics and gaming companies.