Spotify has received a patent on technology that aims to determine what type of music to curate and recommend based on users’ speech and background noise, reports Music Business Worldwide. The company applied for the patent in 2018; it was approved on January 12, 2021.
The patent describes possible applications of technology in which “intonation, stress, rhythm and similar units of speech” are extracted from the user’s voice. The technology could also use speech recognition to identify metadata points such as emotional state, gender, age, accent, and even the environment – that is, whether someone is alone or with other people – based on audio recordings.
The patent application describes how Spotify currently uses a decision tree that shows users different artists, genres, and more to refine the recommendation algorithm for the user. “What is needed is a completely different approach to collecting taste attributes from a user, particularly one that is rooted in technology so that the human activity described above (e.g., requiring a user to provide input) at least partially eliminated and more is carried out efficiently ”, it says in the file. Find the patent below.
It is currently unclear whether Spotify has created a roadmap for implementing this technology in its desktop or mobile apps, or what that implementation might look like. It’s also unclear whether the technology currently exists or whether the patent is speculative. It should be noted that it is not uncommon for tech companies to patent technologies that don’t make it to market.
Pitchfork reached out to Spotify representatives for further comments.
Read “Could Spotify’s New Detection Mode Be Considered Payola?” over in the square.
