New Sensors and Pattern Recognition Techniques for String Instruments

Tobias Großhauser, Ulf Großekathöfer, and Thomas Hermann

Proceedings of the International Conference on New Interfaces for Musical Expression

Abstract:

Pressure, motion, and gesture are important parameters inmusical instrument playing. Pressure sensing allows to interpret complex hidden forces, which appear during playinga musical instrument. The combination of our new sensorsetup with pattern recognition techniques like the lately developed ordered means models allows fast and precise recognition of highly skilled playing techniques. This includes leftand right hand analysis as well as a combination of both. Inthis paper we show bow position recognition for string instruments by means of support vector regression machineson the right hand finger pressure, as well as bowing recognition and inaccurate playing detection with ordered meansmodels. We also introduce a new left hand and chin pressuresensing method for coordination and position change analysis. Our methods in combination with our audio, video,and gesture recording software can be used for teachingand exercising. Especially studies of complex movementsand finger force distribution changes can benefit from suchan approach. Practical applications include the recognitionof inaccuracy, cramping, or malposition, and, last but notleast, the development of augmented instruments and newplaying techniques.

Citation:

Tobias Großhauser, Ulf Großekathöfer, and Thomas Hermann. 2010. New Sensors and Pattern Recognition Techniques for String Instruments. Proceedings of the International Conference on New Interfaces for Musical Expression. DOI: 10.5281/zenodo.1177779

BibTeX Entry:

  @inproceedings{Grosshauser2010,
 abstract = {Pressure, motion, and gesture are important parameters inmusical instrument playing. Pressure sensing allows to interpret complex hidden forces, which appear during playinga musical instrument. The combination of our new sensorsetup with pattern recognition techniques like the lately developed ordered means models allows fast and precise recognition of highly skilled playing techniques. This includes leftand right hand analysis as well as a combination of both. Inthis paper we show bow position recognition for string instruments by means of support vector regression machineson the right hand finger pressure, as well as bowing recognition and inaccurate playing detection with ordered meansmodels. We also introduce a new left hand and chin pressuresensing method for coordination and position change analysis. Our methods in combination with our audio, video,and gesture recording software can be used for teachingand exercising. Especially studies of complex movementsand finger force distribution changes can benefit from suchan approach. Practical applications include the recognitionof inaccuracy, cramping, or malposition, and, last but notleast, the development of augmented instruments and newplaying techniques.},
 address = {Sydney, Australia},
 author = {Gro{\ss}hauser, Tobias and Gro{\ss}ekath\"{o}fer, Ulf and Hermann, Thomas},
 booktitle = {Proceedings of the International Conference on New Interfaces for Musical Expression},
 doi = {10.5281/zenodo.1177779},
 issn = {2220-4806},
 keywords = {left hand,nime10,ordered means models,pressure,sensor,strings},
 pages = {271--276},
 title = {New Sensors and Pattern Recognition Techniques for String Instruments},
 url = {http://www.nime.org/proceedings/2010/nime2010_271.pdf},
 year = {2010}
}