Dorien Herremans

Composing first species counterpoint with a variable neighbourhood search algorithm

In this article, a variable neighbourhood search (VNS) algorithm is developed that can generate musical fragments consisting of a melody for the cantus firmus and the first species counterpoint. The objective function of the algorithm is based on a quantification of existing rules for counterpoint. The VNS algorithm developed in this article is a local search algorithm that starts from a randomly generated melody and improves it by changing one or two notes at a time. A thorough parametric analysis of the VNS reveals the significance of the algorithms parameters on the quality of the composed fragment, as well as their optimal settings. A comparison of the VNS algorithm with a developed genetic algorithm shows that the VNS is more efficient. The VNS algorithm has been implemented in a user-friendly software environment for composition, called Optimuse. Optimuse allows a user to specify a number of characteristics such as length, key and mode. Based on this information, Optimuse ‘composes’ both cantus firmus and first species counterpoint. Alternatively, the user may specify a cantus firmus, and let Optimuse compose the accompanying first species counterpoint.

Dance Hit Song Prediction

Record companies invest billions of dollars in new talent around the globe each year. Gaining insight into what actually makes a hit song would provide tremendous benefits for the music industry. In this research we tackle this question by focussing on the dance hit song classification problem. A database of dance hit songs from 1985 until 2013 is built, including basic musical features, as well as more advanced features that capture a temporal aspect. A number of different classifiers are used to build and test dance hit prediction models. The resulting best model has a good performance when predicting whether a song is a ‘top 10’ dance hit versus a lower listed position.

Generating structured music for bagana using quality metrics based on Markov models

We combine machine learning and optimization techniques to generate music.We study novel ways of using a Markov model to construct an objective function.A Markov model is combined with repetitive and cyclic aspects of a music template.We show the effectiveness of the methods on Ethiopian bagana songs. In this research, a system is built that generates bagana music, a traditional lyre from Ethiopia, based on a first order Markov model. Due to the size of many datasets it is often only possible to get rich and reliable statistics for low order models, yet these do not handle structure very well and their output is often very repetitive. A first contribution of this paper is to propose a method that allows the enforcement of structure and repetition within music, thus handling long term coherence with a first order model. The second goal of this research is to explain and propose different ways in which low order Markov models can be used to build quality assessment metrics for an optimization algorithm. These are then implemented in a variable neighborhood search algorithm that generates bagana music. The results are examined and thoroughly evaluated.

Composing fifth species counterpoint music with a variable neighborhood search algorithm

In this paper, a variable neighborhood search (VNS) algorithm is developed and analyzed that can generate fifth species counterpoint fragments. The existing species counterpoint rules are quantified and form the basis of the objective function used by the algorithm. The VNS developed in this research is a local search metaheuristic that starts from a randomly generated fragment and gradually improves this solution by changing one or two notes at a time. An in-depth statistical analysis reveals the significance as well as the optimal settings of the parameters of the VNS. The algorithm has been implemented in a user-friendly software environment called Optimuse. Optimuse allows a user to input basic characteristics such as length, key and mode. Based on this input, a fifth species counterpoint fragment is generated by the system that can be edited and played back immediately.

Classification and generation of composer-specific music using global feature models and variable neighborhood search

In this article a number of musical features are extracted from a large musical database and these were subsequently used to build four composer-classification models. The first two models, an if–then rule set and a decision tree, result in an understanding of stylistic differences between Bach, Haydn, and Beethoven. The other two models, a logistic regression model and a support vector machine classifier, are more accurate. The probability of a piece being composed by a certain composer given by the logistic regression model is integrated into the objective function of a previously developed variable neighborhood search algorithm that can generate counterpoint. The result is a system that can generate an endless stream of contrapuntal music with composer-specific characteristics that sounds pleasing to the ear. This system is implemented as an Android app called FuX.

FuX, an Android app that generates counterpoint

This paper describes the implementation of an Android application, called FuX, that can continuously play a stream of newly generated fifth species counterpoint. A variable neighborhood search algorithm is implemented in order to generate the music. This algorithm is a modification of an algorithm developed previously by the authors to generate musical fragments of a pre-specified length [28]. The changes in the algorithm allow the Android app to play a continuous stream of music. The objective function used to evaluate the quality of the fragment is based on a quantification of the extensive rules of this musical style. FuX is a user friendly application that can be installed on any Android phone of tablet.

MorpheuS: generating structured music with constrained patterns and tension

Automatic music generation systems have gained in popularity and sophistication as advances in cloud computing have enabled large-scale complex computations such as deep models and optimization algorithms on personal devices. Yet, they still face an important challenge, that of long-term structure, which is key to conveying a sense of musical coherence. We present the MorpheuS music generation system designed to tackle this problem. MorpheuS’ novel framework has the ability to generate polyphonic pieces with a given tension profile and long- and short-term repeated pattern structures. A mathematical model for tonal tension quantifies the tension profile and state-of-the-art pattern detection algorithms extract repeated patterns in a template piece. An efficient optimization metaheuristic, variable neighborhood search, generates music by assigning pitches that best fit the prescribed tension profile to the template rhythm while hard constraining long-term structure through the detected patterns. This ability to generate affective music with specific tension profile and long-term structure is particularly useful in a game or film music context. Music generated by the MorpheuS system has been performed live in concerts.

MorpheuS: automatic music generation with recurrent pattern constraints and tension profiles

Generating music with long-term structure is one of the main challenges in the field of automatic composition. This article describes MorpheuS, a music generation system. MorpheuS uses state-of-the-art pattern detection techniques to find repeated patterns in a template piece. These patterns are then used to constrain the generation process for a new polyphonic composition. The music generation process is guided by an efficient optimization algorithm, variable neighborhood search, which uses a mathematical model of tonal tension to derive its objective function. The ability to generate music according to a tension profile could be useful in a game or film music context. Pieces generated by MorpheuS have been performed in live concerts.

A Multi-modal Platform for Semantic Music Analysis: Visualizing Audio-and Score-Based Tension

Musicologists, music cognition scientists and others have long studied music in all of its facets. During the last few decades, research in both score and audio technology has opened the doors for automated, or (in many cases) semi-automated analysis. There remains a big gap, however, between the field of audio (performance) and score-based systems. In this research, we propose a web-based Interactive system for Multi-modal Music Analysis (IMMA), that provides musicologists with an intuitive interface for a joint analysis of performance and score. As an initial use-case, we implemented a tension analysis module in the system. Tension is a semantic characteristic of music that directly shapes the music experience and thus forms a crucial topic for researchers in musicology and music cognition. The module includes methods for calculating tonal tension (from the score) and timbral tension (from the performance). An audio-to-score alignment algorithm based on dynamic time warping was implemented to automate the synchronization between the audio and score analysis. The resulting system was tested on three performances (violin, flute, and guitar) of Paganinis Caprice No. 24 and four piano performances of Beethovens Moonlight Sonata. We statistically analyzed the results of tonal and timbral tension and found correlations between them. A clustering algorithm was implemented to find segments of music (both within and between performances) with similar shape in their tension curve. These similar segments are visualized in IMMA. By displaying selected audio and score characteristics together with musical score following in sync with the performance playback, IMMA offers a user-friendly intuitive interface to bridge the gap between audio and score analysis.

A variable neighborhood search algorithm to generate piano fingerings for polyphonic sheet music

A piano fingering indicates which finger should play each note in a piece. Such a guideline is very helpful for both amateur and experienced players in order to play a piece fluently. In this paper, we propose a variable neighbourhood search algorithm to generate piano fingerings for complex polyphonic music, a frequently encountered case that was ignored in previous research. The algorithm takes into account the biomechanical properties of the pianist’s hand in order to generate a fingering that is user-specific and as easy to play as possible. An extensive statistical analysis was carried out in order to tune the parameters of the algorithm and evaluate its performance. The results of computational experiments show that the algorithm generates good fingerings that are very similar to those published in sheet music books.