Spotify wants to curate songs based on your emotions. The streaming giant was just granted a patent for a new technology that figures out your “emotional state, gender, age or accent,” based on your speech and suggests music based on those factors.

Spotify reportedly filed for the patent three years ago. It detects “intonation, stress, rhythm and the likes of units of speech,” all while taking background noise into account to guess whether the listener is alone or with the company. The idea for the patent came about because Spotify believed its current method for recommending music is not sophisticated enough.

“What is needed is an entirely different approach to collecting taste attributes of a user, particularly one that is rooted in technology so that the above-described human activity (e.g., requiring a user to provide input) is at least partially eliminated and performed more efficiently,” notes the patent. There isn’t much news yet on exactly how Spotify plans on implementing the technology and when it will potentially be launched, but it’s worth noting that the streaming giant frequently files for patents and that some of them don’t necessarily end up being used.

VIA