Learning Audio Embeddings with User Listening Data for Content-based Music Recommendation
This addresses the problem of recommending new tracks in the music industry, but it is incremental as it builds on existing metric learning and Siamese network approaches.
The paper tackles personalized recommendation for new music releases by learning audio embeddings from user listening data and demographics, achieving state-of-the-art performance on content-based music recommendation tested with millions of users and tracks.
Personalized recommendation on new track releases has always been a challenging problem in the music industry. To combat this problem, we first explore user listening history and demographics to construct a user embedding representing the user's music preference. With the user embedding and audio data from user's liked and disliked tracks, an audio embedding can be obtained for each track using metric learning with Siamese networks. For a new track, we can decide the best group of users to recommend by computing the similarity between the track's audio embedding and different user embeddings, respectively. The proposed system yields state-of-the-art performance on content-based music recommendation tested with millions of users and tracks. Also, we extract audio embeddings as features for music genre classification tasks. The results show the generalization ability of our audio embeddings.