Iterative Meditations: The use of audio feature extraction tools on acousmatic composition
Resumo
This piece explores some possibilities of using Music Information Retrieval and Signal Processing techniques to extract acoustic features from recorded material and use this data to inform the decision making process that is intrinsic to music composition. By trying to identify or create sound descriptors that correlate to the composer’s subjective sensations of listening it was possible to compare and manipulate samples on the basis of this information, bridging the gap between the imagined acoustic targets and the actions required to achieve it. “Iterative Meditations” was created through an iterative process of listening, analyzing, acting and refining the analysis techniques used, having as end product the musical piece itself as well as gathering a collection of tools for writing music.
Referências
Chirs Cannam. The vamp audio analysis plugin api: A programmer’s guide. Availble online: http://vamp-plugins. org/guide. pdf, 2009.
Chris Cannam, Christian Landone, and Mark Sandler. Sonic visualiser: An open source application for viewing, analysing, and annotating music audio files. In Proceedings of the 18th ACM international conference on Multimedia, pages 1467–1468. ACM, 2010.
Thiago Campolina, Maurı́cio Loureiro, and Davi Mota. Expan: a tool for musical expressiveness analysis. In Proceedings of the 2nd International Conference of Students of Systematic Musicology, pages 24–27. IPEM-Institute for Psychoacoustics and Electronic Music Ghent, 2009.
Xavier Serra et al. Musical sound modeling with sinusoids plus noise. Musical signal processing, pages 91–122, 1997.
D Mazzoni and R Dannenberg. Audacity [software]. The Audacity Team, Pittsburg, PA, USA, 2000.
