Google publishes hundreds of research papers every year covering almost everything. From time to time we have seen many different algorithms, which aim to make our life easier. So at the moment a new upcoming one is being "baked". project which is set to be unveiled later this month. It aims to give us the best AI (artificial intelligence) assistant we've ever had.
You may have encountered difficulty when trying to use something like Google Now, and you are not connected to the Web.
So, the Google Research team is trying to develop a new, personalized system for voice commands and dictation that works within your device instead of asking for help from a server. All this without needing too much space on your device.
To educate the new project, around 2.000 hours of anonymous Google voice searches are used, total over 100 million statements, and YouTube's noise is used to mimic the noisy real-life conditions.
By application a series of complex computational models and enough compression on the files so that they take up as little disk space as possible, the team has come up with a local voice system that runs on average seven times faster than real-time on a Nexus 5, while using only 20,3 MB.
As with Google Now voice commands, it can manipulate first names and other information from the device to perform special tasks, such as sending an email post officey in a contact. Instructions can be recorded, and stored in case you are away online.
The results of the new project will be presented at 41 International Conference on Acoustics, Speech and Signal Processing, which will start on March 20.
