Affective Music Information Retrieval

Abstract

Much of the appeal of music lies in its power to convey emotions/moods and to evoke them in listeners. In consequence, the past decade witnessed a growing interest in modeling emotions from musical signals in the music information retrieval (MIR) community. In this article, we present a novel generative approach to music emotion modeling, with a specific focus on the valence-arousal (VA) dimension model of emotion. The presented generative model, called acoustic emotion Gaussians (AEG), better accounts for the subjectivity of emotion perception by the use of probability distributions. Specifically, it learns from the emotion annotations of multiple subjects a Gaussian mixture model in the VA space with prior constraints on the corresponding acoustic features of the training music pieces. Such a computational framework is technically sound, capable of learning in an online fashion, and thus applicable to a variety of applications, including user-independent (general) and user-dependent (personalized) emotion recognition and emotion-based music retrieval. We report evaluations of the aforementioned applications of AEG on a largerscale emotion-annotated corpora, AMG1608, to demonstrate the effectiveness of AEG and to showcase how evaluations are conducted for research on emotion-based MIR. Directions of future work are also discussed.

V-SVR+: Support Vector Regression With Variational Privileged Information

“…• The acoustic emotion Gaussians (AEG) model [54] is a generative model which learns from the emotion annotations of multiple subjects in the valence and arousal spaces.…”

Affective recommender systems in online news industry: how emotions influence reading choices

“…Until recently, relatively little research has been conducted on using affective features in the design of recommender systems. Most previous work focused on the utilization of personality traits for personalization of recommender systems (Nunes and Hu 2012), with the special focus on the music domain (Andjelkovic et al 2016;Strle et al 2016;Wakil et al 2015;Wang et al 2015). For instance Andjelkovic et al (2016) present a recommender system that selects subsequent songs based on the mood and affective features of songs.…”

Introduction to Intelligent Music Systems and Applications

“…State-of-the-art algorithms allow a user to create a music playlist of desired emotions by specifying a point or drawing a trajectory in a low-dimensional emotion space. Personalization techniques that learn from a user's feedback can be further employed to account for the subjective nature of emotion perception [Wang et al 2016]. It is also possible to actively and continuously detect a listener's emotional state from physiological, facial, or textual cues and to recommend music in a personalized and "mood-optimizing" way [Yang and Chen 2012;Ferwerda and Schedl 2014].…”