Descriptors for Perception of Quality in Jazz Piano Improvisation

Jeff Gregorio, David Rosen, Michael Caro, and Youngmoo E. Kim

Proceedings of the International Conference on New Interfaces for Musical Expression

Abstract:

Quality assessment of jazz improvisation is a multi-faceted, high-level cognitive task routinely performed by educators in university jazz programs and other discriminating music listeners. In this pilot study, we present a novel dataset of 88 MIDI jazz piano improvisations with ratings of creativity, technical proficiency, and aesthetic appeal provided by four jazz experts, and we detail the design of a feature set that can represent some of the rhythmic, melodic, harmonic, and other expressive attributes humans recognize as salient in assessment of performance quality. Inherent subjectivity in these assessments is inevitable, yet the recognition of performance attributes by which humans perceive quality has wide applicability to related tasks in the music information retrieval (MIR) community and jazz pedagogy. Preliminary results indicate that several musiciologically-informed features of relatively low computational complexity perform reasonably well in predicting performance quality labels via ordinary least squares regression.

Citation:

Jeff Gregorio, David Rosen, Michael Caro, and Youngmoo E. Kim. 2015. Descriptors for Perception of Quality in Jazz Piano Improvisation. Proceedings of the International Conference on New Interfaces for Musical Expression. DOI: 10.5281/zenodo.1179072

BibTeX Entry:

  @inproceedings{jgregorio2015,
 abstract = {Quality assessment of jazz improvisation is a multi-faceted, high-level cognitive task routinely performed by educators in university jazz programs and other discriminating music listeners. In this pilot study, we present a novel dataset of 88 MIDI jazz piano improvisations with ratings of creativity, technical proficiency, and aesthetic appeal provided by four jazz experts, and we detail the design of a feature set that can represent some of the rhythmic, melodic, harmonic, and other expressive attributes humans recognize as salient in assessment of performance quality. Inherent subjectivity in these assessments is inevitable, yet the recognition of performance attributes by which humans perceive quality has wide applicability to related tasks in the music information retrieval (MIR) community and jazz pedagogy. Preliminary results indicate that several musiciologically-informed features of relatively low computational complexity perform reasonably well in predicting performance quality labels via ordinary least squares regression.},
 address = {Baton Rouge, Louisiana, USA},
 author = {Jeff Gregorio and David Rosen and Michael Caro and {Youngmoo E.} Kim},
 booktitle = {Proceedings of the International Conference on New Interfaces for Musical Expression},
 doi = {10.5281/zenodo.1179072},
 editor = {Edgar Berdahl and Jesse Allison},
 issn = {2220-4806},
 month = {May},
 pages = {327--328},
 publisher = {Louisiana State University},
 title = {Descriptors for Perception of Quality in Jazz Piano Improvisation},
 url = {http://www.nime.org/proceedings/2015/nime2015_331.pdf},
 year = {2015}
}