Created an open analogue of Siri - Sirius, available under the BSD license

The Clarity Lab team , based at the University of Michigan, offers an open source solution for a personal computer assistant. Their program recognizes the voice and looks for answers to requests, just like Siri from Apple, Google Now from Google, and similar solutions from Microsoft and Amazon do. A project called Sirius can do even more than its analogues - for example, you can provide him with a picture and ask a question about it.

The project is sponsored by Google, DARPA, the US military and the US National Science Foundation. It is distributed under the BSD license , which means complete openness and free of charge for everyone. This means that any startups will be able to implement such functionality in their projects and devices.


The principle of the system

But for this they will have to figure out the rather complex system that the project uploaded to GitHub consists of . The system requires additional separate programs - Sphinx , Kaldi, Protobuf, Speeded Up Robust Features ( SURF , runs on OpenCV). At the ASPLOS 2015 conference, developers will present both their scientific work on the project and the tutorial on installing and working with it.

Among the enthusiasts there have already been attempts to create an analogue of Siri - for example, JuliusJS , a library for speech recognition. But so far, noticeable results from these projects are not visible.