Let’s agree to disagree: Consensus Entropy Active Learning for Personalized Music Emotion Recognition (ISMIR 2021)
This work was made with Estefanía Cano, Yi-Hsuan Yang, Perfecto Herrera, and Emilia Gómez, and was funded by the TROMPA EU project. It was presented in the 22nd International Society for Music Information Retrieval Conference (ISMIR).
Abstract
Previous research in music emotion recognition (MER) has tackled the inherent problem of subjectivity through the use of personalized models – models which predict the emotions that a particular user would perceive from music. Personalized models are trained in a supervised manner, and are tested exclusively with the annotations provided by a specific user. While past research has focused on model adaptation or reducing the amount of annotations required from a given user, we propose a methodology based on uncertainty sampling and query-by-committee, adopting prior knowledge from the agreement of human annotations as an oracle for active learning (AL). We assume that our disagreements define our personal opinions and should be considered for personalization. We use the DEAM dataset, the current benchmark dataset for MER, to pre-train our models. We then use the AMG1608 dataset, the largest MER dataset containing multiple annotations per musical excerpt, to re-train diverse machine learning models using AL and evaluate personalization. Our results suggest that our methodology can be beneficial to produce personalized classification models that exhibit different results depending on the algorithms’ complexity.
You can see a presentation of our work in here and go to our open source code.