by Katherine E. Shoichet | CNN
Stanford students heard sadness in their friend’s voice when they shared the news.
“Guys, I had to quit my job.”
For them, it meant nothing. He was fluent in English and Spanish, extremely friendly and an expert in systems engineering. Why couldn’t he stop the call center job?
Her accent, the friend said, made it difficult for many customers to understand; Some people even insulted him because of the way he spoke.
All three students felt that the problem was bigger than their friend’s experience. So he founded a startup to solve it.
Now his company, Sunus, is testing artificial intelligence-powered software that aims to eliminate miscommunication by changing people’s tone in real time. For example, a call center employee in the Philippines may speak normally into the microphone and end up sounding like a Kansas customer on the other end.
Startup founders say call centers are only the beginning. The company’s website touts its plans as “speech, reimagined.”
Eventually, they expect the app they’re developing will be used by a wide variety of industries and individuals. It could help doctors understand patients better, he says, or help grandchildren understand their grandparents better.
“We have a very grand vision for Sunus,” says CEO Maxim Serebryakov.
And for Serebryakov and his co-founders, the project is personal.
People’s ‘voices are not being heard as much as their voices’
The three who founded Sunus met at Stanford University, but they are all from radically different countries – Serebryakov, now CEO, is from Russia; Andres Pérez Soderi, now Chief Financial Officer, is from Venezuela; And Sean Zhang, who is now chief technology officer, is from China.
He is no longer a Stanford student. Serebryakov and Perez have graduated; Zhang dropped out to focus on bringing Sunus to life.
He launched the company last year, and gave it a name that can be easily pronounced in different languages ”to highlight our global mission and desire to bring people closer together,” Perez says.
Over the years, all three say they’ve experienced how accents can get in the way.
“We all come from international backgrounds. We’ve seen firsthand why people treat you differently because of the way you speak,” Serebryakov says. “It’s heartbreaking sometimes.”
Zhang says her mother, who immigrated to the United States from China more than 20 years ago, still talks to the cashier when they go grocery shopping together because she is embarrassed.
“That’s why I joined Max and Andres in building this company, trying to help people who think their voices aren’t being heard as much as their accent,” he says. Huh.
Serebryakov says he has seen how he is treated in hotels when his parents come to visit him in the United States – how people make assumptions when they hear his accent.
“They speak a little louder. They change their behavior,” he says.
Perez says that after attending a British school, he first struggled to understand the American accent when he arrived in the United States.
And don’t get him started about what happens when his dad tries to use the Amazon Alexa that his family gave him for Christmas.
“We found out quickly that, when Alexa was turning on the lights in random places in the house and making them pink, Alexa didn’t understand my father’s accent at all,” Perez says.
Call centers are testing technology
English is the most used language in the world. An estimated 1.5 billion people speak it – and most of them are not native speakers. In the United States alone, millions of people speak English as a second language.
This has created a growing market for apps that help users practice their English pronunciation. But Sunus is using AI to take a different approach.
The premise is that instead of learning to pronounce words differently, technology can do it for you. There will no longer be a need for expensive or time-consuming pronunciation reduction training. And the understanding will be almost instantaneous.
Serebryakov says he is aware that people’s accents and identities can be closely linked, and stresses that the company is not trying to erase accents, or imply that one way of speaking is different from another. is better.
“We don’t allow people to change the way they speak to hold a position, to do a job. Identity and pronunciation are important. They are intertwined,” he says. “You never want someone to be Change your pronunciation to satisfy someone.”
Currently, Sunus’s algorithm can convert English to American, Australian, British, Filipino, Indian and Spanish accents, and the team plans to add more. They can add a new utterance to the system by training a neural network with audio recordings from professional actors and other data – a process that takes several weeks.
The Suns team made two appearances for CNN. In one, a person with an Indian accent is heard reading a series of literary sentences. Then the same phrases convert to the American pronunciation:
Another example contains phrases that may be more common in a call center setting, such as “If you give me your full name and order number, we can go ahead and start making corrections for you.”
The American-accented results sound somewhat artificial and paused, as do virtual-assistant voices like Siri and Alexa, but Perez says the team is working on improving the technology.
“The accent changes, but the tone is maintained,” he says. “We’re continuing to work on how to make the result as natural and emotional and exciting as possible.”
Initial response from call centers that are trying the technology has been positive, says Perez. So submit comments on their website as the word about their venture spreads.
And he says his plans for the company garnered $5.5 million in seed funding from investors earlier this year.
How startup founders see its future
This allowed Sunus to increase its workforce. Most of the Palo Alto employees of the California-based company come from international backgrounds. And this is no coincidence, says Serebryakov.
“What we’re building has resonated with so many people, even the people we hire. … It’s really exciting to see,” he says.
While the company is growing, there may still be times when Sanaas shows up in the App Store or on a cell phone near you.
The team says they are working with large call center outsourcing companies right now and opting for a slower rollout for individual users so that they can refine the technology and ensure security.
But ultimately, they hope Sunus will be used by anyone who needs it — in other areas as well.
Perez envisions it to play an important role in helping people communicate with their doctors.
“Any second that gets lost in a misunderstanding due to either lost time or the wrong message is potentially very, very impressive,” he says. “We really want to make sure nothing is lost in translation.”
He says that someday, it could help people learn languages, improve dubbing in movies, and help smart speakers in homes and voice assistants in cars understand different accents.
The Sunus team is also hoping to add other languages to the algorithm – and not just in English.
The three co-founders are still working out the details. But how this technology could improve communication in the future, he says, is something that’s easy to understand.
™ and © 2021 Cable News Network, Inc., WarnerMedia Co. All rights reserved.