Download Dynamic Stochastic Wavetable Synthesis
Dynamic Stochastic Synthesis (DSS) is a direct digital synthesis method invented by composer Iannis Xenakis and notably employed in his 1991 composition GENDY3. In its original conception, DSS generates periodic waves by linear interpolation between a set of breakpoints in amplitude–time space. The breakpoints change position each period, displaced by random walks via high-level parameters that induce various behaviors and timbres along the pitch–noise continuum. The following paper proposes Dynamic Stochastic Wavetable Synthesis as a modification and generalization of DSS that enables its application to table-lookup oscillators, allowing arbitrary sample data to become the basis of a DSS process. We describe the considerations affecting the development of such an algorithm and offer a real-time implementation informed by the analysis.
Download Expressive Piano Performance Rendering from Unpaired Data
Recent advances in data-driven expressive performance rendering have enabled automatic models to reproduce the characteristics and the variability of human performances of musical compositions. However, these models need to be trained with aligned pairs of scores and performances and they rely notably on score-specific markings, which limits their scope of application. This work tackles the piano performance rendering task in a low-informed setting by only considering the score note information and without aligned data. The proposed model relies on an adversarial training where the basic score notes properties are modified in order to reproduce the expressive qualities contained in a dataset of real performances. First results for unaligned score-to-performance rendering are presented through a conducted listening test. While the interpretation quality is not on par with highly-supervised methods and human renditions, our method shows promising results for transferring realistic expressivity into scores.