Google is updating its Google Assistant virtual companion to break communication barriers with users. Starting over the next few days, users will be able to teach Google Assistant to enunciate and recognise names of contacts the way they pronounce them. The software giant says that the Assistant will listen to the pronunciation and remember it “without keeping a recording of the voice.” It claims the update aims to understand users better, especially with complicated names and the way they are pronounced. Additionally, Google Assistant is getting another update to improve its Timer feature. In case a user changes commands in mid-sentence, the Assistant would try and understand the exact inputs without needing a fresh set of voice commands.
Google states it can be frustrating when users are trying to send a text or make a call via Google Assistant, and the AI is unable to recognise names or simply mispronounces contact. “Understanding spoken language is difficult because it is so contextual and varies so much from person to person…We want Assistant to accurately recognise and pronounce people’s names as often as possible, especially those that are less common,” the software giant said in a blog post. Google says the new update will be available in English and would expand to more languages later.
As mentioned, Google Assistant Timer that that essentially works as a countdown timer is getting a big improvement. The update aims to make the virtual assistant more flexible, especially when a user fumbles or stops mid-sentence. Here’s how the company explains the development:
“Maybe you’ve got a 10-minute timer for dinner going at the same time as another to remind the kids to start their homework in 20 minutes. You might fumble and stop mid-sentence to correct how long the timer should be set for, or maybe you don’t use the exact same phrase to cancel it as you did to create it. Like in any conversation, context matters and Assistant needs to be flexible enough to understand what you’re referring to when you ask for help.”
Google will rebuild Assistant’s NLU models to understand the context more accurately, while also improving its “reference resolution” The upgrade further uses machine learning technology powered by state-of-the-art BERT – a technology that the company invented in 2018 and first brought to Search to make it possible to process words in relation to all the other words in a sentence, rather than one-by-one in order.