Spotify has received a patent for technology that aims to use recordings of users’ speech and background noise to determine what type of music should be cured and recommended to them, reports Music Business Worldwide. The company filed for a patent in 2018; was approved on January 12, 2021.
The patent describes the potential uses of technology that involve extracting “intonation, emphasis, rhythm and similar speech 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 – that is, whether someone is alone or with others – based on the audio recording.
The patent application describes how Spotify currently uses a decision tree – showing users different artists, genres and more – to help refine its user recommendation algorithm. “What is needed is a totally different approach to collecting flavor attributes from a user, particularly one that is rooted in technology so that the human activity described above (for example, requiring a user to provide data) is at least partially eliminated and performed more efficiently, ”says the document. Find the patent below.
It is currently unclear whether Spotify has established a roadmap for implementing this technology in its desktop or mobile applications, or what form that implementation can take. It is also unclear whether the technology currently exists or whether the patent is speculative. It should be noted that it is not unusual for technology companies to patent a technology that does not reach the market.
A spokesman for Spotify provided the following statement to Pitchfork:
Read “Can Spotify’s new discovery mode be considered Payola?” over the field.