Feature extraction for voice-driven synthesis

This paper explores the singing voice from an unusual perspective, not as a musical instrument but as a musical controller. A set of spectral processing algorithms extract features form the input voice. These features are categorized in four groups: excitation, vocal tract, voice quality and context. The extracted values are then transmitted as Open Sound Control (OSC) messages in order to be used in an external synthesis engine. In this document, we provide first a technical description of the algorithms, and in a second part, we detail the components of the system. A practical example of voice-driven synthesis using PureData (Pd) is also presented.