Speech Technology Magazine

 

U of Michigan Researchers Develop Open-Source Virtual Assistant

Sirius is free for developers to use to develop their own virtual assistant apps.
Posted Mar 16, 2015
Page1 of 1
Bookmark and Share

Researchers from the University of Michigan's Clarity Lab have built a free open-source digital assistant named Sirius that they say will allow developers to create their own personal assistants.

Sirius combines speech recognition, image matching, natural-language processing, and a question-and-answer system. It was developed using open-source projects that, according to the researchers, use similar techniques and algorithms found in commercial systemslike Microsoft's Cortana, Google Now, and Apple's Siri.

"Unlike Google Now, Siri and Cortana, Sirius is free to use and can be customized as required by anyone interested in the technology. Now the core technology is out of the bag, and we all have access to it," said Jason Mars, an assistant professor of computer science and engineering at the University of Michigan and co-director of Clarity Lab, in a press statement. "Instead of making an app to run on the Apple Watch, for example, maybe I could make my own watch. We're very excited to see what the world comes together to build and learn with Sirius as a starting point."

The Sirius project is just one sign of the growing intelligent virtual assistants market, which Transparency Market Research  valued at $352 million in 2012 and expects to expand at a compound annual growth rate of 30.6 percent through 2019 to reach $2.1 billion.


Page1 of 1