Google publishes hundreds of research papers every year covering everything from algorithms to education and an upcoming project set to be presented later this month seeks to beÂ the best AI assistant you ever had.
You may have already run into difficulty when trying to use something likeÂ Google Now because some commands only work when youâ€™re connected to the Web.
So the Google Research team is working on creating a new, personalized system for voice commands, as well as dictation, that works on your device rather than being dealt withÂ server-side, allÂ without taking up too much room on your handset.
To train it, they used around 2,000 hours of anonymizedÂ Google voice search traffic, totalling more than 100 million utterances,Â while adding in noise from YouTube to imitate real-life speaking conditions.
By applying a number of complex computational and compression models, the team has come up with a local voice system that runs on average seven times faster than real-time on a Nexus 5, all while taking up just 20.3 MB of storage.
Like Google Now voice commands,Â it can handle proper names and other device-specific information for tasks â€“ like sending an email to a contact â€“ and instructionsÂ can be logged,Â stored and then dealt with when youâ€™re back online if necessary.
The findings will be presented at the 41st International Conference on Acoustics, Speech and Signal Processing, which is happening from March 20.