Title :
Perceptsynth: mapping perceptual musical features to sound synthesis parameters
Author :
Groux, Sylvain Le ; Verschure, Paul FMJ
Author_Institution :
Lab. for SyntheticPerceptive, Emotive & Cognitive Syst., Univ. Pompeu Fabra, Barcelona
fDate :
March 31 2008-April 4 2008
Abstract :
This paper presents a new system that allows for intuitive control of an additive sound synthesis model from perceptually relevant high-level sonic features. We suggest a general framework for the extraction, abstraction, reproduction and transformation of timbral characteristics of a sound analyzed from recordings. We propose a method to train, tune and evaluate our system in an automatic, consistent and reproducible fashion, and show that this system yields various original audio and musical applications.
Keywords :
acoustic signal processing; learning (artificial intelligence); musical acoustics; signal synthesis; additive sound synthesis model; intuitive control; machine learning approach; perceptsynth method; perceptual musical feature mapping; sound generation; timbral characteristics; training method; Additives; Control system synthesis; Feature extraction; Frequency; Machine learning; Matrix decomposition; Network synthesis; Principal component analysis; Signal synthesis; Timbre; Feature Extraction; SVM; Sound Synthesis;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4244-1483-3
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2008.4517562
