Thanks to new research from the University of Waterloo, home entertainment platforms will soon better understand user queries.

In collaboration with the University of Maryland and Comcast Applied Artificial Intelligence (AI) Research Lab, the researchers have successfully applied AI technology to create the most natural, speech-based interactions with televisions thus far.

"Today, we have become accustomed to talking to intelligent agents that do our bidding — from Siri on a mobile phone to Alexa at home. Why shouldn't we be able to do the same with TVs?" asked Jimmy Lin, a professor at the University of Waterloo and chair in the David R. Cheriton School of Computer Science.

"Comcast's Xfinity X1 aims to do exactly that — the platform comes with a 'voice remote' that accepts spoken queries. Your wish is its command — tell your TV to change channels, ask it about free kids' movies, and even about the weather forecast."

Using an AI technique called hierarchical recurrent neural networks, the team improved the system’s ability to understand voice queries posed by users. At the production stage, the new neural network model was used to answer user queries and demonstrated the ability to handle even the most difficult queries.

"If a viewer asks for 'Chicago Fire,' which refers to both a drama series and a soccer team, the system is able to decipher what you really want," said Lin. "What's special about this approach is that we take advantage of context — such as previously watched shows and favorite channels — to personalize results, thereby increasing accuracy."

The paper, Multi-Task Learning with Neural Networks for Voice Query Understanding Entertainment Platform, was presented at the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining held recently in the U.K.