• Corpus ID: 35143736

An update on the SOMax project

  title={An update on the SOMax project},
  author={Laurent Bonnasse-Gahot},
Apprentissage de structures multi-dimensionnelles pour l'improvisation musicale
L'improvisation automatique est un domaine recent issu des etudes sur la creativite artificielle. Les systemes actuels d'improvisation automatique sont capables de prendre en consideration des
Somax 2: A Real-time Framework for Human-Machine Improvisation
A modular framework for real-time, human-machine improvisation that improvises over an audio or MIDI corpus by recombining its content, while listening and adapting to incomingaudio or MIDI signals.
Apprentissage de structures musicales en contexte d'improvisation. (Learning of musical structures in the context of improvisation)
Dans un premier temps, nous presentons un systeme capable of suivre la logique contextuelle d’une improvisation representee par un oracle des facteurs tout en enrichissant son discours musical a l’aide de connaissances multidimensionnelles representees par des modeles probabilistes interpoles.
ImproteK: Introducing Scenarios into Human-Computer Music Improvisation
The article deals with the integration of temporal specifications in the music generation process by means of a fixed or dynamic “scenario” and addresses the issue of the dialectic between reactivity and planning in interactive music improvisation.
Guiding human-computer music improvisation: introducing authoring and control with temporal scenarios. (Guider l'improvisation musicale homme-machine : introduire du contrôle et de la composition avec des scénarios temporels)
A music generation model guided by a formal structure; a framework to compose improvised interactive performances at the ``scenario'' level; an architecture combining anticipatory behavior with reactivity using mixed static/dynamic scheduling techniques; an audio rendering module to perform live re-injection of captured material in synchrony with a non-metronomic beat.
Improvising in Creative Symbolic Interaction
Creative Symbolic Interaction brings together the advantages from the worlds of interactive real-time computing and intelligent, content-level analysis and processing, in order to enhance and
Reflecting on the Musicality of Machine Learning based Music Generators in Real-Time Jazz Improvisation: A case study of OMax-ImproteK-Djazz
This work looks at improvisations produced by the OMax, ImproteK, and Djazz ML generators, through the lens of the elements of music and suggests a musically-oriented evaluation methodology. This
Augmenting an improvised practice on the viola da gamba
This thesis examines my improvisatory practice on the viola da gamba and its augmentation with mixed-music computer systems. It comprises creative work and an extended written commentary and
Application to human-computer improvisation
The aim is to develop a software that interacts in real-time with a musician by inferring expected structures and provide short term predictions of the musical structures to improve the quality of the computer co-improvisation.


3 Navigating Tonal Space
The question of how tonal structures in music are perceived and represented by the human mind has been approached by multiple disciplines, primarily music theory and cognitive psychology, and more
A Perceptual Model of Pulse Salience and Metrical Accent in Musical Rhythms
In Experiment 1, six cyclically repeating interonset interval patterns (1,2:1,2:1:1,3:2:1,3:1:2, and 2:1:1:2) were each presented at six different note rates (very slow to very fast). Each trial
Timbre Similarity: Convergence of Neural, Behavioral, and Computational Approaches
The results of the present study suggest that timbre representations reflected in behavioral measures correspond to neural activity, both as measured directly and as simulated in self-organizing neural network models.
Evaluation of the Audio Beat Tracking System BeatRoot
Improvements to the original BeatRoot system and a large-scale evaluation and analysis of the system's performance are described, with results compared with other evaluations such as the MIREX 2006 Audio Beat Tracking Evaluation.
The Cortical Topography of Tonal Structures Underlying Western Music
In functional magnetic resonance imaging experiments, an area in the rostromedial prefrontal cortex that tracks activation in tonal space was identified and the tonality structure was maintained as a dynamic topography in cortical areas known to be at a nexus of cognitive, affective, and mnemonic processing.
Measuring and Modeling Real-Time Responses to Music: The Dynamics of Tonality Induction
A variety of real-time responses evoked by a single piece of music, the organ Duetto BWV 805 by J S Bach, were examined, with results closely matching those of the concurrent probe-tone data.
A Matlab Toolbox for Music Information Retrieval
We present MIRToolbox, an integrated set of functions written in Matlab, dedicated to the extraction from audio files of musical features related, among others, to timbre, tonality, rhythm or form.
Using Factor Oracles for Machine Improvisation
The factor oracle, a data structure proposed by Crochemore & al for string matching, is presented and the relation between this structure and the previous models is shown and how it can be adapted for learning musical sequences and generating improvisations in a real-time context.
OMaxist Dialectics: Capturing, Visualizing and Expanding Improvisations
A novel visualization is proposed, which displays the current state of the learnt knowledge and allows to notice, both on the fly and a posteriori, points of musical interest and higher level structures.