Spotify suggests music by analyzing your speech and emotional state

In October 2020, Spotify was granted a patent for technology that would allow them to analyze a user’s personality to create music suggestions.

To do this, Spotify will analyze a user’s mood, favourite genres of music, and their demographic to create a “personality” for the user. Spotify would use this analysis to then offer music suggestions based on the analyzed factors. 

A new patent that was recently published stated that Spotify would go even deeper into the mind of a user to make these recommendations even more specific. They now would use “speech recognition” to determine the user’s “emotional state, gender, age or accent”. 

The new patent titled “Identification of taste attributes from an audio signal” was filed in February, 2018 and was granted on January 12, 2021. You can read about the full patent here. 

Spotify’s new patent states that it covers a “method for processing a provided audio signal that includes speech content and background noise” followed by “identifying playable content, based on the processed audio signal content.”

The patent filing continues: “The user is then further asked to provide additional information to narrow down the number even further. In one example, the user is pushed to a decision tree including, e.g., artists or shows that the user likes, and fills in or selects options to further fine-tune the system’s identification of their tastes”.