Impress: A Machine Learning Approach to Soundscape Affect Classification for a Music Performance Environment

Miles Thorogood, and Philippe Pasquier

Proceedings of the International Conference on New Interfaces for Musical Expression

Abstract

Soundscape composition in improvisation and performance contexts involves manyprocesses that can become overwhelming for a performer, impacting on thequality of the composition. One important task is evaluating the mood of acomposition for evoking accurate associations and memories of a soundscape. Anew system that uses supervised machine learning is presented for theacquisition and realtime feedback of soundscape affect. A model of sound-scape mood is created by users entering evaluations of audio environmentsusing a mobile device. The same device then provides feedback to the user ofthe predicted mood of other audio environments. We used a features vector ofTotal Loudness and MFCC extracted from an audio signal to build a multipleregression models. The evaluation of the system shows the tool is effective inpredicting soundscape affect.

Citation

Miles Thorogood, and Philippe Pasquier. 2013. Impress: A Machine Learning Approach to Soundscape Affect Classification for a Music Performance Environment. Proceedings of the International Conference on New Interfaces for Musical Expression. DOI: 10.5281/zenodo.1178674 [PDF]

BibTeX Entry

@inproceedings{Thorogood2013,
 abstract = {Soundscape composition in improvisation and performance contexts involves manyprocesses that can become overwhelming for a performer, impacting on thequality of the composition. One important task is evaluating the mood of acomposition for evoking accurate associations and memories of a soundscape. Anew system that uses supervised machine learning is presented for theacquisition and realtime feedback of soundscape affect. A model of sound-scape mood is created by users entering evaluations of audio environmentsusing a mobile device. The same device then provides feedback to the user ofthe predicted mood of other audio environments. We used a features vector ofTotal Loudness and MFCC extracted from an audio signal to build a multipleregression models. The evaluation of the system shows the tool is effective inpredicting soundscape affect.},
 address = {Daejeon, Republic of Korea},
 author = {Miles Thorogood and Philippe Pasquier},
 booktitle = {Proceedings of the International Conference on New Interfaces for Musical Expression},
 doi = {10.5281/zenodo.1178674},
 issn = {2220-4806},
 keywords = {soundscape, performance, machine learning, audio features, affect grid},
 month = {May},
 pages = {256--260},
 publisher = {Graduate School of Culture Technology, KAIST},
 title = {Impress: A Machine Learning Approach to Soundscape Affect Classification for a Music Performance Environment},
 url = {http://www.nime.org/proceedings/2013/nime2013_157.pdf},
 year = {2013}
}