Join us at TNW Conference 2021 for insights into the future of tech →

The heart of tech

This article was published on March 11, 2016


Google’s working on a new version of Now that won’t need a data connection

Google’s working on a new version of Now that won’t need a data connection
Kirsty Styles
Story by

Kirsty Styles

Reporter

Kirsty Styles is a journalist who lives in Hackney. She was previously editor at Tech City News and is now a reporter at The Next Web. She l Kirsty Styles is a journalist who lives in Hackney. She was previously editor at Tech City News and is now a reporter at The Next Web. She loves tech for good, cleantech, edtech, assistive tech, politech (?), diversity in tech.

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 be the best AI assistant you ever had.

You may have already run into difficulty when trying to use something like Google Now because some commands only work when you’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 with server-side, all without taking up too much room on your handset.

To train it, they used around 2,000 hours of anonymized Google voice search traffic, totalling more than 100 million utterances, 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, it can handle proper names and other device-specific information for tasks – like sending an email to a contact – and instructions can be logged, stored and then dealt with when you’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.

➤ Personalized speech recognition on mobile devices [Google via ZDNet]