Using Deep learning methods for generation of a personalized list of shuffled songs

TL;DR

This paper proposes a deep learning approach using convolutional deep belief networks and multi-layer perceptrons to generate personalized shuffled song playlists based on genre recognition and user preferences.

Contribution

It introduces a novel method combining genre recognition and playlist metadata to create more human-like, personalized shuffled music playlists.

Findings

Effective genre classification from audio features.

Personalized playlists better match user preferences.

Improved user satisfaction with shuffled music experience.

Abstract

The shuffle mode, where songs are played in a randomized order that is decided upon for all tracks at once, is widely found and known to exist in music player systems. There are only few music enthusiasts who use this mode since it either is too random to suit their mood or it keeps on repeating the same list every time. In this paper, we propose to build a convolutional deep belief network(CDBN) that is trained to perform genre recognition based on audio features retrieved from the records of the Million Song Dataset. The learned parameters shall be used to initialize a multi-layer perceptron which takes extracted features of user's playlist as input alongside the metadata to classify to various categories. These categories will be shuffled retrospectively based on the metadata to autonomously provide with a list that is efficacious in playing songs that are desired by humans in normal conditions.