Spotify Patents Tech To Monitor Users’ Speech and Emotions for Song Recommendations

Spotify has reportedly been granted a patent for technology that will allow the streaming giant to monitor their users' speech and suggest music based on their "emotional state, gender, age, or accent."

Music Business Worldwide reports that the company filed for the patent all the way back in 2018, and it was approved on Jan. 12, 2021. Among the potential uses of the technology, which will use recordings of listener speech plus background noise, would be to deduce the "intonation, stress, rhythm, and the likes of units of speech." The tech could even be used to deduce the environment people are listening to music in, and could figure out whether someone is alone or has company.

Spotify has yet to detail what the implementation of this tech would look like, or when it might happen. It's also worth noting that patents can be granted for technology that currently doesn't exist, as many companies frequently patent hypothetical or speculative technology. The inspiration behind the move, according to the patent, is that the current method for recommending music, which usually involves asking the user template questions, isn't quite efficient 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," the patent reads.

Reached for comment, a Spotify spokesperson told Complex, "Spotify has filed patent applications for hundreds of inventions, and we regularly file new applications. Some of these patents become part of future products, while others don't. Our ambition is to create the best audio experience out there, but we don't have any news to share at this time."