Sirius, the open-source intelligent personal assistant set to take on Siri
Fri 20 Mar 2015
Researchers at the University of Michigan have this week released the open-source virtual assistant Sirius to rival Apple’s Siri and Microsoft’s Cortana.
The new personal voice-activated assistant was created by developers at the university’s Clarity Labs. Unlike its commercial lock-in counterparts, Sirius is free and can be easily customised. Anyone can contribute to the open-source project via GitHub, with the code released under the BSD license making the software free both to use and to distribute. The project is supported by Google, the Defense Advanced Research Projects Agency (DARPA) and the National Science Foundation.
The Michigan researchers explain in the academic paper ‘Sirius: An Open End-to-End Voice and Vision Personal Assistant and Its Implications for Future Warehouse Scale Computers’ [PDF] that the Sirius project aims to create “an open end-to-end IPA web-service application that accepts queries in the form of voice and images, and responds with natural language.”
For now the Sirius technology has only been tested on Ubuntu desktops, but the developers hope to soon roll the programming onto smartphones and other mobile devices.
In a video released by the group, lead researcher Jason Mars describes Sirius as a Linux-like version of Siri. Although the open-source assistant is perhaps not yet as streamlined as its rivals, Sirius does offer a greater range of capabilities through its integration with other well-established open-source solutions such as Carnegie Mellon University’s Sphinx speech recognition, and OpenEphyra – a question and answer system based on IBM’s Watson. With Sirius for example, a user can take a picture and ask a question about it which Siri and Cortana are yet to enable.
“What we’ve done with Sirius is pushed the limits of the traditional intelligent personal assistant,” said Johann Hauswald, a fellow computer science student at the Clarity Lab. “Not only can you interact with your voice but you can also ask questions about what you’re seeing, which is a new way to interact with this type of device.”
To access Sirius users will need to download each of the integrated open-source algorithms, but the research group have made them available as a download suite, along with a tutorial on how to get the system to work.
“Now the core technology is out of the bag, and we all have access to it,” said Mars. “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.”
Mars believes the Sirius platform could signal important developments in next-generation data centre computing. He sees Sirius giving researchers in the field a ‘testbed’ for querying how data centres which process voice commands should best evolve to keep up with increasing demand from wearable technology and IoT, which are heavily fuelled by voice and image input in the cloud.
“We have to think of new ways to redesign our cloud platforms to support this type of workload,” Mars added.