Method, system, and medium for emotional music recommendation and composition

Abstract

A method, system, and medium for recommending and composing emotional music. The method identifies a listener's current emotional state and a target emotional state, and generates an audio stream, e.g., a music playlist, with the intent of generating a controlled trajectory of the listener's emotional state from the current state to the target state. The audio stream is generated by a machine learning system trained using data from the listener and / or other users indicating the effectiveness of particular audio segments, i.e., audio segments with particular features, in generating the desired emotional trajectory. The audio stream is presented to the user as an auditory stimulus. The machine learning system can be updated based on changes in the emotional state induced in the listener after exposure to the auditory stimulus. Over time, the machine learning system acquires a robust interpretation of the relationship between music and human emotions, so that the machine learning system can also be used to compose, master, and / or adapt music designed to elicit specific emotional responses in listeners.

Images