Major tech companies like Apple and Microsoft have been able to provide millions of people with personal digital assistants on mobile devices, allowing people to do things like set alarms or get answers to questions simply by speaking. Now, other companies can implement their own versions, using new open-source software called Sirius — an allusion, of course, to Apple’s Siri.
Today researchers from the University of Michigan are giving presentations on Sirius at the International Conference on Architectural Support for Programming Languages and Operating Systems in Turkey. Meanwhile, Sirius also made an appearance on Product Hunt this morning.
“Sirius … implements the core functionalities of an IPA (intelligent personal assistant) such as speech recognition, image matching, natural language processing and a question-and-answer system,” the researchers wrote in a new academic paper documenting their work. The system accepts questions and commands from a mobile device, processes information on servers, and provides audible responses on the mobile device.
Some startups have been striving to develop their own smart assistants, but none has yet been able to challenge Apple, Google, or Microsoft. Perhaps following the arrival of Sirius, that could change.
The researchers sought to assemble a “representative of production grade systems.” Indeed, the speech recognition component of Sirius incorporates deep learning, an increasingly trendy type of artificial intelligence that involves training deep neural networks on extensive amounts of data and then having them make inferences about new data based on what they already know.
In addition to documenting their personal digital assistant, the researchers also ran tests to determine the best types of server chips for handling a complex workload like Sirius.
“We show that GPU- and FPGA-accelerated servers can improve the query latency on average by 10x and 16x,” they wrote. “Leveraging the latency reduction, GPU- and FPGA-accelerated servers can reduce the TCO [total cost of ownership] by 2.6x and 1.4x, respectively.”
And here’s a video of University of Michigan doctoral student Johann Hauswald demonstrating Sirius in a command-line interface: