In this paper, we propose a novel algorithm for score-informed tracking of the fundamental frequency over the duration of single tones. The tracking algorithm is based on a peak-picking algorithm over spectral magnitudes and ensures time-continuous f0-curves. From a set of 19 jazz solos from three saxophone and three trumpet players, we collected a set of 6785 f0-contours in total. We report th...

In the context of contemporary monophonic music, expression can be seen as the difference between a musical performance and its symbolic representation, i.e. a musical score. In this paper, we show how Maximum Entropy (MaxEnt) models can be used to generate musical expression in order to mimic a human performance. As a training corpus, we had a professional pianist play about 150 melodies of ja...

This article provides a first introduction to some formal and computational models applied in the analysis and generation of popular music (including rock, jazz, and chanson). It summarizes the main philosophy underlying the project entitled “Modèles formels dans et pour la musique pop, le jazz et la chanson”, which constitutes one of the research axes of the GDR ESARS (Esthétique, Art & Scienc...

We report here on current works on the MusES environment, designed for experimenting with various objectoriented knowledge representation techniques in the field of tonal harmony. The first layer of MusES is a repository of consensus knowledge about tonal harmony, including an explicit representation of enharmonic spelling, as well as representation of intervals, scales and chords that support ...

This paper applies methods of interactional analysis to the video recording of a musical performance in Fez, Morocco, with the understanding that performance is most essentially a communicative phenomenon (Bauman, 1984). Music and interaction are the subject of Monson’s (1996) groundbreaking work on improvisation and interaction in jazz. Monson demonstrates that “jazz can be seen as a musical l...

The analysis of melodies symbolically represented as digital scores (standard MIDI files) is studied. A number of melodic, harmonic, and rhythmic statistical descriptors are computed. Their representation ability is analyzed using the principal components technique (PCA). Also their ability to separate two particular musical styles, like jazz and classical, using a per-feature separability test...

We analyze a dataset providing the complete information on the effective plays of thousands of music listeners during several months. Our analysis confirms a number of properties previously highlighted by research based on interviews and questionnaires, but also uncover new statistical patterns, both at the individual and collective levels. In particular, we show that individuals follow common ...

Music audio structure segmentation has been a task in the Music Information Retrieval Evaluation eXchange (MIREX) since 2009. In 2010, five algorithms were evaluated against two datasets (297 and 100 songs) with an almost exclusive focus on western popular music. A new annotated dataset significantly larger in size and with a more diverse range of musical styles became available in 2011. This n...