Using Deep learning methods for generation of a personalized list of shuffled songs
This addresses a specific issue for music enthusiasts by providing a more tailored listening experience, though it appears incremental as it builds on existing deep learning methods for music classification.
The paper tackles the problem of shuffle modes in music players being too random or repetitive by proposing a convolutional deep belief network for genre recognition, which is then used to generate personalized shuffled playlists based on user preferences and metadata.
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.