Wearable translation device promises a science-fiction future, almost

(Waverly Labs)

A company called Waverly Labs is working on a wearable translation device that has captured people’s imaginations, generated plenty of buzz, and raised over $3 million on Indiegogo.

Its promise? That two people wearing earpieces made by the company could speak in different languages, and with the earpieces working in conjunction with a smartphone app, each person could hear a translation in their preferred language in their ear. For example, one person could speak Spanish, and the other would hear it as English in his ear, and vice versa.

The idea is undoubtedly exciting to anyone who has felt the limits of a language barrier. And a video that the company posted that demonstrates the device in action, translating between English and French, has been viewed over 280,000 times. Still, some are skeptical. For Forbes, Paul Armstrong wrote that he was not convinced that the product is actually real. And Snopes.com is also dubious, saying the tech is “unproven.”

But Andrew Ochoa, the company’s 34-year-old CEO, and Marion Guerriero, the start-up’s communications director, assured me that it’s real, and that it works.

Ochoa, who’s from Texas and speaks a little Spanish, was wearing a black dress shirt and dark blue jeans and was fighting a persistent, nagging cough when we spoke in person in September. He’d just returned from a trip overseas.

“I’m just a dreamer,” he said, when I asked him about his professional background, and what led him to make such an intriguing device.

But my first question was: Does it work?

“Absolutely,” Ochoa said.

Each person must have an earpiece in, though, for it to do so. And there is a “nominal” delay of “a couple seconds,” he said, for the device to translate from language to language. The system uses both their own technology and other technology as a “hybrid” system, he explained.

Is it a scam? I asked him a few minutes later. Is it real?

(Waverly Labs)

“We absolutely have a prototype,” he assured me. The company says that they will allow the media to try it in December, and it should be available to the public in May of next year.

“There’s a lot that we want to work on,” he said, and later added: “Just in general, translation is difficult, and it’s not always 100 percent. And we want people to understand it’s not perfect.”

He declined to say what the device’s word-error rate was.

That said, it raises intriguing possibilities. The system can work with more than two earpieces and even more than two languages, he said, meaning that three people could have a conversation— say in French, Spanish, and English— and each could hear the conversation in their chosen language, like a mini United Nations at your kitchen table. This generation of device will support verbal translation in these languages only: English, Spanish, French, Italian, and Portuguese (both Brazilian and from Portugal).

Jim Glass, a senior research scientist at MIT who works in their computer science and artificial intelligence laboratories, said that the three types of technology behind this product— speech recognition, text translation, and text-to-speech synthesis— have been in the works for a while.

“I actually can quite imagine that you could do something like this today," he said, but added: “The devil’s in the details.”

“It’s not going to be the Babel Fish in ‘The Hitchhiker's Guide to the Galaxy’ where it’s constantly just translating on the fly into your ear when you’re in the vicinity of somebody talking a foreign language,” he said. “Although that’s a science fiction dream, and maybe one day we’ll be closer to that.”

Ultimately, the idea of the device is exciting, even if it’s impossible to see how well it works until it’s tested. Besides the Babel Fish, it’s hard not to compare the Pilot device to the concept of the universal translator from “Star Trek,” but Ochoa said he didn’t know if that was a fair comparison.

“We want to be realistic in the sense that on 'Star Trek,' it’s like instantaneous,” he said, snapping his fingers. “This is the first step. This is the first generation. That’s why we call it Pilot.”

Ultimately, the proof will be in the hearing.

Follow Rob Verger on Twitter: @robverger

This article has been updated to clarify a description of the languages the device will verbally translate.