Spotify has granted a patent enabling them to monitor users’ speech. With this access, the streaming platform can collect data to improve their algorithm and extend their music recommendations.
Music Business Worldwide reported this news for the first time. The patent was filed in 2018 and was approved earlier this month on January 12th. In the streaming giant application, Spotify said the technology would work by detecting audio, including voice signals and background noise, to understand ‘content metadata’ about users’ emotional state, gender, age and accents.
The patent also states that Spotify relies on information such as ‘intonation, voltage, rhythm and similar devices’. The platform says that these factors would detect whether a user feels “happy, angry, sad or neutral”.
The streaming platform would also have access to user environments. This technology applies to physical environments, ie whether it is inside or outside the social environment and whether it is alone or with others.
Spotify will be able to collect this information from ‘sounds of vehicles on the street, other people talking, birds chirping, printers printing, and so on’. Spotify claims that it is ‘common’ for a media streaming application to include features that provide personalized media recommendations to a user in the field of on-demand media streaming services. ‘
In a statement issued to Pitchfork earlier today, a company representative said: ‘Spotify has filed patent applications for hundreds of inventions, and we regularly submit new applications. Some of these patents become part of future products, while others do not.
“Our ambition is to provide the best audio experience out there, but we have no news to share at the moment.”