Spotify wants to know your 'emotional state' for music recommendations

(Image credit: Kaspars Grinvalds / Shutterstock)

A Spotify patent has detailed the company's plans to comprise speech recognition into how it makes content recommendations. It's manifestly exploring how information technology could use phonation data to determine a user's emotional state, gender, age or accent — then you could end up with music or podcast recommendations that literally adjust your mood.

The patent, spotted by Music Business organization Worldwide, was filed dorsum in February 2018 but merely granted earlier this month. It details a arrangement wherein a "provided audio bespeak,", presumably microphone input, is analyzed to determine the personal traits of the speaker, equally well as hints to their physical and social environments. Spotify would then suggest content it deems most suitable to the user and their environment.

Apple tree Music vs. Spotify: Which is the all-time music streaming service?
The best wireless headphones for listening to music
Plus: Leaving WhatsApp? Telegram wants to make it simpler to motility over

Spotify is famously adept at making content recommendations based on users' listening habits, but it'southward never attempted to build a personal profile of specific users to the extent detailed in this patent. The proposed system tin can, for instance, use speech recognition to check whether someone is in a positive or negative mental state, and analyze ambient sound to decide whether they're alone or with a group of friends.

The organization would probable propose more upbeat content if information technology thinks you're in a skilful mood and are hanging out with friends, or relaxing music if it thinks yous're solitary and stressed.

"Prosodic information (e.one thousand., intonation, stress, rhythm and the like of units of spoken communication) can be combined and integrated with acoustic information within a hidden Markov model architecture," reads the patent filing. "Using this compages, that prosodic information allows the emotional state of a speaker to be detected and categorized."

Every bit always with newly-discovered patents, peculiarly those filed almost ii years ago, won't necessarily reflect the final product. Spotify could have modified or even entirely ditched its speech recognition plans in that fourth dimension.

Yet, any organization that involves determining a user's personal characteristics, equally well as their current surround, raises serious privacy questions. If Spotify is proceeding with these plans or similar, we'd hope the final product would at least be opt-in feature.

James is currently Hardware Editor at Rock Paper Shotgun, but before that was Audio Editor at Tom'southward Guide, where he covered headphones, speakers, soundbars and anything else that intentionally makes dissonance. A PC enthusiast, he also wrote computing and gaming news for TG, ordinarily relating to how hard it is to find graphics menu stock.