Spotify has granted a patent with technology aimed at using recordings of users’ speech and background noise to determine what kind of music they should compose and recommend, reports Music Business Worldwide. The company filed the patent in 2018; it was approved on January 12, 2021.
The patent outlines potential uses of technology that involve extracting ‘intonation, tension, rhythm and similar units’ from the user’s voice. The technology can also use speech recognition to identify metadata points such as emotional state, gender, age, accent and even environment – ie whether someone is alone or with other people – based on sound recording.
The patent registration sets out how Spotify is currently using a decision tree – which shows users different artists, genres and more – to help refine its recommendation algorithm for the user. ‘What is needed is a very different approach to the collection of taste characteristics of a user, especially one rooted in technology, so that the above human activity (e.g. the requirement of a user to provide input) at least partially eliminated and more executed. efficiently, ”reads the submission. Find the patent below.
It is currently unclear whether Spotify has introduced a roadmap for implementing this technology in its computer or mobile applications, or what form this implementation may take. It is also unclear whether the technology currently exists and whether the patent is speculative. It should be noted that technology companies are not abnormal in patenting technology that is ultimately not on the market.
A Spotify spokesman gave the following statement to Pitchfork:
Read “Can Spotify’s new discovery mode be considered Payola?” past on the Pitch.