Adaptive High-level Classification of Vocal Gestures Within a Networked Sound Instrument. Freeman, J., Ramakrishnan, C., Varnik, K., Neuhaus, M., Burk, P., & Birchfield, D. In pages 4, 2004. International Computer Music Association.
Adaptive High-level Classification of Vocal Gestures Within a Networked Sound Instrument [link]Paper  abstract   bibtex   
We have implemented a high-level vocal gesture classifier which uses Adaptive Principal Component EXtraction (APEX), a neural network implementation of Principal Components Analysis (PCA), to reduce a multi-dimensional space of statistical features into a three-dimensional highlevel feature space. The classifier is used within Auracle, a real-time, collaborative, Internet-based instrument: highlevel features, along with envelope data extracted from lowlevel voice analysis, are used to drive sound synthesis. The APEX neural network is initially trained with a sample database of vocal gestures, and it continues to adapt (both within single user sessions and over longer time periods) in response to user interaction. Both training and evolution are accomplished without supervision, so that the nature of the classifications is determined more by how users interact with the system than by the preconceptions of its designers.
@inproceedings{freeman_adaptive_2004,
	title = {Adaptive {High}-level {Classification} of {Vocal} {Gestures} {Within} a {Networked} {Sound} {Instrument}},
	url = {http://hdl.handle.net/2027/spo.bbp2372.2004.012},
	abstract = {We have implemented a high-level vocal gesture classifier which uses Adaptive Principal Component EXtraction (APEX), a neural network implementation of Principal Components Analysis (PCA), to reduce a multi-dimensional space of statistical features into a three-dimensional highlevel feature space. The classifier is used within Auracle, a real-time, collaborative, Internet-based instrument: highlevel features, along with envelope data extracted from lowlevel voice analysis, are used to drive sound synthesis. The APEX neural network is initially trained with a sample database of vocal gestures, and it continues to adapt (both within single user sessions and over longer time periods) in response to user interaction. Both training and evolution are accomplished without supervision, so that the nature of the classifications is determined more by how users interact with the system than by the preconceptions of its designers.},
	publisher = {International Computer Music Association},
	author = {Freeman, Jason and Ramakrishnan, C. and Varnik, Kristjan and Neuhaus, Max and Burk, Phil and Birchfield, David},
	year = {2004},
	pages = {4},
}

Downloads: 0