About

VMO-Score (Arias et al., 2016) is a tool to generate an interactive score to control the improvisation according to larger structures found in an audio recording.

Intuitively, VMO-Score takes an audio file as an input and uses the tool VMO (Wang and Dubnov, 2015) to generate an Audio Oracle (Dubnov et al., 2011) for improvisation. In addition, VMO is also used to do a segmentation analysis of the input (Wang and Mysore, 2016). Once the tool has identified possible natural transitions between sections with similar musical content, it translates the musical structure into a Petri net (Murata, 1989) model in order to provide a higher, more intuitive and formal representation of this structure. Therefore, the artist can modify the structure of the Petri net in order to control the improvisation by adding temporal and logical constraints.

VMO-Score also generates an interactive score based on the Petri net structure for the inter-media sequencer i-score (dlHogue et al., 2016). This tool provides a complete graphical interface for structuring and performing in real-time the improvisation. Such improvisation is carried out by the Max interface of the Audio Oracle called PyOracle (Surges and Dubnov, 2013) which is controlled by i-score using OSC [1] messages.

summary
[1]Open Sound Control (OSC) is a protocol for communication among multimedia devices.

Bibliography

Jaime Arias, Myriam Desainte-Catherine, and Shlomo Dubnov. Automatic Construction of Interactive Machine Improvisation Scenarios from Audio Recordings. In 4th International Workshop on Musical Metacreation, MUME 2016, Paris, France, June 27 – July 1, 2016. 2016. URL: http://bit.ly/2mCAmDZ. ↩

Théo de la Hogue, Jean-Michaël Celerier, and Pascal Baltazar. Presentation d'un Formalisme Graphique pour l'Ecriture de Scenarios Interactifs. In Journées d'Informatique Musicale, JIM 2016, Albi, France, March 31 - April 2, 2016, 37–41. Albi, 2016. ↩

Shlomo Dubnov, Gerard Assayag, and Arshia Cont. Audio Oracle Analysis of Musical Information Rate. In 2011 IEEE Fifth International Conference on Semantic Computing, 567–571. IEEE, sep 2011. doi:10.1109/ICSC.2011.106. ↩

Tadao Murata. Petri Nets: Properties, Analysis and Applications. Proceedings of the IEEE, 1989. doi:10.1109/5.24143. ↩

Greg Surges and Shlomo Dubnov. Feature Selection and Composition Using PyOracle. In AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment. 2013. URL: https://www.aaai.org/ocs/index.php/AIIDE/AIIDE13/paper/view/7452. ↩

Cheng-i Wang and Shlomo Dubnov. The Variable Markov Oracle: Algorithms for Human Gesture Applications. IEEE MultiMedia, 22(4):52–67, oct 2015. doi:10.1109/MMUL.2015.76. ↩

Cheng-I Wang and Gautham J. Mysore. Structural Segmentation with the Variable Markov Oracle and Boundary Adjustment. In The 41st IEEE International Conference on Acoustics, Speech and Signal Processing. Shanghai, China, 2016. IEEE. ↩