Anna Aljanaki

Emotional Analysis of Music: A Comparison of Methods

Music as a form of art is intentionally composed to be emotionally expressive. The emotional features of music are invaluable for music indexing and recommendation. In this paper we present a cross-comparison of automatic emotional analysis of music. We created a public dataset of Creative Commons licensed songs. Using valence and arousal model, the songs were annotated both in terms of the emotions that were expressed by the whole excerpt and dynamically with 1 Hz temporal resolution. Each song received 10 annotations on Amazon Mechanical Turk and the annotations were averaged to form a ground truth. Four different systems from three teams and the organizers were employed to tackle this problem in an open challenge. We compare their performances and discuss the best practices. While the effect of a larger feature set was not very apparent in the static emotion estimation, the combination of a comprehensive feature set and a recurrent neural network that models temporal dependencies has largely outperformed the other proposed methods for dynamic music emotion estimation.

Developing a benchmark for emotional analysis of music

Music emotion recognition (MER) field rapidly expanded in the last decade. Many new methods and new audio features are developed to improve the performance of MER algorithms. However, it is very difficult to compare the performance of the new methods because of the data representation diversity and scarcity of publicly available data. In this paper, we address these problems by creating a data set and a benchmark for MER. The data set that we release, a MediaEval Database for Emotional Analysis in Music (DEAM), is the largest available data set of dynamic annotations (valence and arousal annotations for 1,802 songs and song excerpts licensed under Creative Commons with 2Hz time resolution). Using DEAM, we organized the ‘Emotion in Music’ task at MediaEval Multimedia Evaluation Campaign from 2013 to 2015. The benchmark attracted, in total, 21 active teams to participate in the challenge. We analyze the results of the benchmark: the winning algorithms and feature-sets. We also describe the design of the benchmark, the evaluation procedures and the data cleaning and transformations that we suggest. The results from the benchmark suggest that the recurrent neural network based approaches combined with large feature-sets work best for dynamic MER.

Content-based music recommendation using underlying music preference structure

The cold start problem for new users or items is a great challenge for recommender systems. New items can be positioned within the existing items using a similarity metric to estimate their ratings. However, the calculation of similarity varies by domain and available resources. In this paper, we propose a content-based music recommender system which is based on a set of attributes derived from psychological studies of music preference. These five attributes, namely, Mellow, Unpretentious, Sophisticated, Intense and Contemporary (MUSIC), better describe the underlying factors of music preference compared to music genre. Using 249 songs and hundreds of ratings and attribute scores, we first develop an acoustic content-based attribute detection using auditory modulation features and a regression by sparse representation. We then use the estimated attributes in a cold start recommendation scenario. The proposed content-based recommendation significantly outperforms genre-based and user-based recommendation based on the root-mean-square error. The results demonstrate the effectiveness of these attributes in music preference estimation. Such methods will increase the chance of less popular but interesting songs in the long tail to be listened to.

Designing Games with a Purpose for Data Collection in Music Research. Emotify and Hooked: Two Case Studies

Collecting ground truth data for music research requires large amounts of time and money. To avoid these costs, researchers are now trying to collect information through online multiplayer games with the underlying purpose of collecting scientific data. In this paper we present two case studies of such games created for data collection in music information retrieval (MIR): Emotify, for emotional annotation of music, and Hooked, for studying musical catchiness. In addition to the basic requirement of scientific validity, both applications address essential development and design issues, for example, acquiring licensed music or employing popular social frameworks. As such, we hope that they may serve as blueprints for the development of future serious games, not only for music but also for other humanistic domains. The pilot launch of these two games showed that their models are capable of engaging participants and supporting large-scale empirical research.

Tonic: Combining Ranking and Clustering Dynamics for Music Discovery

This paper describes the design of Tonic, a novel web interface for music discovery and playlist creation. Tonic maps songs into a two dimensional space using a combination of free tags, metadata, and audio-derived features. Search results are presented in this two dimensional space using a combination of clustering and ranking visualization strategies. Tonic was ranked first in the 2014 MIREX User Experience Grand Challenge, where it was evaluated in terms of learnability, robustness and overall user satisfaction, amongst others.