Note: This bibliographic page is archived and will no longer be updated. For an up-to-date list of publications from the Music Technology Group see the Publications list .

Algorithmic Prediction of Music Complexity Judgements

Title Algorithmic Prediction of Music Complexity Judgements
Publication Type Conference Paper
Year of Publication 2006
Conference Name 9th International Conference on Music Perceptionand Cognition
Authors Streich, S. , & Herrera P.
Abstract Background
With the huge amount of music available in form of digital audio files today, new methods for management and retrieval are in demand. It is therefore a key aspect to obtain semantically meaningful descriptions of music without the need for costly and unreliable manual annotation. We focus here on the algorithmic prediction of music complexity, which is known to be related to subjective liking and thus forms an interesting descriptor for automated music recommendation.

Aims
In the research presented here, we evaluate the accuracy of algorithmic music complexity predictions. Several algorithms are considered that compute complexity estimates solely based on the music audio signal. The different algorithms focus each one on a different musical facet (e.g. rhythm, instrumentation, harmonies). In order to test the capacities of these algorithms (individually and jointly) we match their output against subjective complexity ratings collected through a listening test and look for significant correlations.

Method
In the listening test subjects were asked to rate up to 30 music excerpts that were randomly picked from a collection of 82 tracks. Rating consisted on judging the complexity of the music and also indicating their familiarity with and their liking of each excerpt. Additionally, in a separate part of the survey, data about the subjects' usual music listening habits were collected. An automatic analysis of musical features was used to build predictive models of the excerpts' complexity.

Results
In order to evaluate the models we have used a subset of 43 excerpts, those that have been consistently and coherently rated by most of our 16 listeners. With this set, we found some significant correlations between the averaged subjects' ratings and the algorithmic predictions. In particular, a simple rhythmic complexity model and a model based on the loudness fluctuations by themselves were already significant at the p<0.05 level.

Conclusions
While for certain music it seems impossible to give a correct complexity prediction, since among human listeners there will be no agreement either, for other types of music it emerges that algorithmic complexity predictions are feasible to a certain degree by only relying on the audio signal.