Deep Machine Learning for Parameter Estimation in Physical Modelling
This page contains sound examples and figures from the paper "Introducing Deep Machine Learning for Parameter Estimation in Physical Modelling" submitted to DAFx-17.
Abstract:
One of the most challenging tasks in physically-informed sound synthesis is the estimation of model parameters to produce a desired timbre. Automatic parameter estimation procedures have been developed in the past for some specific parameters or application scenarios but, up to now, no approach has been proved applicable to a wide variety of use cases. A general solution to parameters estimation problem is provided along this paper which is based on a supervised convolutional machine learning paradigm. The described approach can be classified as ``end-to-end'' and requires, thus, no specific knowledge of the model itself. Furthermore, parameters are learned from data generated by the model, requiring no effort in the preparation and labeling of the training dataset. To provide a qualitative and quantitative analysis of the performance, this method is applied to a patented digital waveguide pipe organ model, yielding very promising results.
Sound examples
- Original A4 tone "Stentor"
- Generated A4 tone "Stentor"
- Original A4 tone "HW-DE"
- Generated A4 tone "HW-DE"
Figures
Spectra and harmonic content for two A4 tones from (a) Principal stop named ``Stentor'', and (c) Principal stop named ``HW-DE''. The gray lines and crosses show the spectrum and the harmonic peaks of s(n), while the black line and dots show the spectrum and the harmonic peaks of s^(n).