Give the Gift of Voice

February 14, 2014

Since deliv­ering a lec­ture at TED Women in December, North­eastern Uni­ver­sity asso­ciate pro­fessor Rupal Patel has had her work cut out for her. In con­junc­tion with her talk, Patel launched a web­site called VocalId​.org in an attempt to crowd-​​source the cre­ation of per­son­al­ized syn­thetic voices for indi­vid­uals with severe speech impairment.

Patel, a speech com­mu­ni­ca­tion expert who holds joint appoint­ments in the Bouvé Col­lege of Health Sci­ence and the Col­lege of Com­puter and Infor­ma­tion Sci­ence, has been cre­ating sim­ilar voices for a number of years. To do so, she takes a small sample of the dis­or­dered speaker’s voice and infuses it into a library of recorded vocal­iza­tions from a healthy speaker of a sim­ilar back­ground. But so far, the process has been much dif­ferent from what she now envisions.

For one thing, the cur­rent pro­tocol requires voice donors to visit her lab and record two to three hours of speech. Addi­tion­ally, the equip­ment used in those recording ses­sions is expen­sive and rather high technology.

“If we’re to make a real dif­fer­ence in the hun­dreds of peo­ples’ lives who want their own voice, we need to stream­line the process,” said Patel.

Enter The Human Voice­bank Ini­tia­tive. Patel’s goal is to bank 1 mil­lion voice sam­ples by 2020. Within a couple of weeks of her TED talk, she had already col­lected hun­dreds of poten­tial donors as well as requests from a slew of people inter­ested in having a voice cre­ated just for them. To meet the growing demand, which is sure to increase now that the video is avail­able to the public, Patel and her team are working to create a more user-​​friendly voice-​​banking interface.

Patel and her team plan hope that donors will be able to use the rel­a­tively high quality micro­phone on their own smart­phones and tablets to record them­selves. They plan to turn the process into some­thing of a game, where donors are encour­aged by in-​​app incen­tives to return again and again to do more recording. Addi­tion­ally, they envi­sion cre­ating a learning cur­riculum to teach young people about the sci­ence of speech as they progress through the recording process.

“There’s a lot of work to be done but we are excited about the payoff,” said Patel. “We expect this new approach to help a lot more people than we ever could have done previously.”

People inter­ested in donating their voices can sign up at VocalID​.org, where they may also donate their time, exper­tise, and finan­cial support.

Footage courtesy of TEDWomen2013.