Micah Fowler, left, and Cedric Yarbrough participate in the "Speechless" panel during the Disney/ABC Television Critics Association summer press tour in Beverly Hills, California, August 4, 2016.
Ryan. Alex. Siri. These are names of voices that are used on cellphones or computers. They also have become voices for people with speech problems who use technology to talk.

Now some scientists are making voices to sound more like the people who use them. To do it, they work with a group of people who are sharing their voices with those who cannot speak.

Md. Teen Is One Of 17,000 Voice Donors

The effort to build a worldwide "Human Voicebank" has attracted more than 17,000 volunteers from 110 countries. One is Priyanka Pandya from Columbia, Maryland. She is 16 years old. She plans to spend her winter vacation recording a string of sentences into her computer.

Her voice could be used to help one of more than 2 million Americans who have speech problems and need help to talk. It's a problem shown in the television series "Speechless." The main character is a teenager with cerebral palsy, which affects muscle use. He depends on technology and a helper to act as his "voice" at school.

"Everyone has a voice," said Rupal Patel. She started VocaliD, the company that launched the voicebank. "Even people who are speechless have sounds" that are only theirs, she said.

VocaliD Combines Volunteer And User Voices

Her company designs custom voices by recording the sounds of the user. Then those sounds are blended with six to 10 hours of recordings from a voice volunteer, matched to the user.

The company is making voices now for its first 100 customers, but scientists have been studying the technology for years.

Tim Bunnell is head of the Speech Research Laboratory at the Alfred I. DuPont Hospital for Children in Wilmington, Delaware. He has created voices for more than 1,000 people with diseases. Some were able to record their own voices before they lost the ability to talk.

The scientists in Bunnell's lab study the user's sounds for qualities such as pitch. Then they get the recordings from a voice volunteer. They put the voices together by changing the volunteer voice to sound like the user's voice.

Patel is also a speech professor on leave from Northeastern University. She worked with Bunnell as a scientist. She developed her own way of blending voices and turned to the online world for help. The goal was to have enough voices to reflect the differences of customers, which could include a man from Alabama or a little girl from Ireland.

Voicebank Was Launched Two Years Ago

Since she announced the voicebank two years ago, she said, many have helped. Volunteers ages 6 to 91 logged on all over the world. People help for many reasons. Some are practicing English or doing community service. Some have diseases and could one day receive voice help.

Pandya began recording her voice last summer using headphones and speaking into her computer. Then she asked friends to do the same.

Patel said she is working to make it simpler to build voices. The $1,249 cost is too high for many people. For volunteers, it can take six to 10 hours to record the needed speech. Only about one out of 10 makes it all the way through.

"Like Getting Something Back That Was Stolen"

Some of the first customers say they are happy with the results.

John Gregoire, of Windham, Maine, was one of the first to receive a customized voice last December from VocaliD. It was eight years after he learned he had an illness. His voice had become unclear to everyone except his wife and youngest son.

His wife, Linda, said she got used to hearing him speak with "Ryan," the voice in his computer. When they heard his new voice, they reacted together instantly. Linda said, "It was him."

"Having a distinctive voice is like getting something back that was stolen," John said.

]]>