New technology lets Spotify choose songs based on user moods

In the battle between streaming services for greater personalisation offerings, Spotify has new technology to identify a user’s mood.

First filed in 2018 and finally patented on January 12, according to the BBC, the speech recognition tech allows Spotify to suggest songs based on the user’s emotional state (sad, happy, stressed, vindictive), gender, accent or age.

Age can be “roughly” determined based on “a combination of vocal tract length and pitch”.

The patent claimed it can even create a playlist based on detecting by background noises, for example, if the user is alone, with others or at a party.

Such recommendations have been confirmed by past Spotify studies digging more into users’ heads, with one published in December 2020, tying in music taste with people’s personalities.

Those who saw themselves as “open to new experiences” tended to be drawn to classical, Afropop or “sentimental” like Miles Davis’ ‘Freddie Freeloader’ and ‘April Come She Will’ by Simon & Garfunkel.

Blues or “brooding music” (‘Take Care’ by Drake, ‘Karma Police’ by Radiohead) is for those wanting “emotional stability,” while listening to soul or ‘lively’ music (‘Down On The Corner’ by Creedence Clearwater Revival, ‘Let The Good Times Roll’ by Ray Charles) correlates positively.

Fans of Death Metal or “aggressive” music (e.g. ‘Boss’ by Lil Pump, ‘Last Resort’ by Papa Roach) tended to have less “agreeable” self-assessments, while people who listen to jazz or country had more.

In the past four months, Spotify’s patents have included a karaoke-like feature which allows users to lay their own vocals on a music track, and a “cadence- based media content selection engine” which matches the tempo of users’ music to their running speed.