AMUSE (Advanced MUSic Explorer) was created 2006 as an open-source Java framework for various music information retrieval tasks like feature extraction, feature processing, classification, and evaluation. In contrast to toolboxes which focus on individual MIR-related algorithms, it is possible with AMUSE, for instance, to extract features with Librosa, process them based on events estimated by MIRtoolbox, classify with WEKA or Keras, and validate the models with own classification performance measures. We present several substantial contributions to AMUSE since its first presentation at ISMIR 2010. They include the annotation editor for single and multiple tracks, the support of multi-label and multi-class classification, and new plugins which operate with Keras, Librosa, and Sonic Annotator. Other integrated methods are the structural complexity processing, chord vector feature, aggregation of features around estimated onset events, and evaluation of time event extractors. Further advancements are a more flexible feature extraction with different parameters like frame sizes, possibility to integrate additional tasks beyond algorithms related to supervised classification, marking of features which can be ignored for a classification task, extension of algorithm parameters with external code (e.g., a structure of a Keras neural net), etc.

The concept of structural complexity describes the temporal progress of feature values on different time scales. We apply it to audio features with the goal to classify music files into genres using k-Nearest Neighbors and Random Forest. We use a publicly available data set of 1550 music tracks which are labeled as belonging to one of six different genres (or to none of them). The classification models are trained with the help of eight feature sets that describe different musical aspects (chords, harmony, instruments, timbre, etc.) in order to find out which features are best suited to predict these genres using the structural complexity. We apply evolutionary multi-objective feature selection to measure individual contributions of different structural complexity features for each genre to feature sets with the smallest classification errors. We also introduce a new feature chord vector which is shown to perform significantly better on genre classification with the structural complexity method than the chord features used in a previous work. The statistical analysis of time scales and features leads to several recommendations for the setup of feature processing based on structural complexity.