Real-Time Performance Controllers For Synthesized Singing
Perry R. Cook · 2005
A wide variety of singing synthesis models and methods exist,but there are remarkably few real-time controllers for thesemodels. This paper describes a variety of devices developedover the last few years for controlling singing synthesismodels implemented in the Synthesis Toolkit in C++ (STK),Max/MSP, and ChucK. All of the controllers share somecommon features, such as air-pressure sensing for breathingand/or loudness control, means to control pitch, and methodsfor selecting and blending phonemes, diphones, and words.However, the form factors, sensors, mappings, and algorithmsvary greatly between the different controllers.