A US Spotify patent – ‘Identification of Taste Attributes From an Audio Signal’ – originally filed in 2018, has now been granted starting January 12, allowing the streaming service to track a user’s daily speech in an effort to provide personalized recommendations to the user.
This patent also extends to background noise in addition to everyday speech and will help the platform determine a user’s ’emotional state, gender, age or accent’ and aims to quantify this data by attributing the input to a range of emotions : ‘happy, sad, angry or neutral’, reports Music Business Worldwide.
These moods are determined by a number of factors, and Spotify will track “intonation, stress, rhythm, and similar units of speech” to make those determinations.
Currently Spotify is already collecting some of this personal information through a short questionnaire, but this approach is now considered outdated and “tedious” to the user. Basically, all those options you have to put in place when setting up your profile are out of favor, so Spotify can listen to anything you say, even if it’s a bird chirping outside or cars driving past.
To further explain the clear need for this intrusive data collection methodology, the petitioner states: “What is needed is an entirely different approach to collecting a user’s flavor attributes, particularly one rooted in technology, so that the human activity, requiring input from a user) is at least partially eliminated and performed more efficiently.
Whatever Spotify recommends to you in the future, at least we still have this AI bot that will toast your taste in music.