Voice transformation algorithms with real time DSP rapid prototyping tools

Bertini G, Fontana F, Gonzalez D, Grassi L, Magrini M

Digital Signal Processing  Audio Restoration  Rapid Prototyping  C.3 Signal Processing and Systems  H.5.1 Audio Input/Output  H.5.5 Sound and Music Computing  I.5.4 Waveform Analysis 

The main goal of the work here described is the DSP implementation of innovative algorithms for real-time voice transformation. This work represents part of the procedure (developed in the framework of the RACINE-S European Project) conceived for reconstructing voice and dialogue in audio tracks of old and highly damaged film movies. Besides the implementation of a set of methods, as LPC/ VC (Linear Prediction Coding/ Voice Conversion),innovative methods of improving of the quality of synthesized voice have been considered. This whole set of operations represents a particular implementation of the so-called 'Virtual Dubbing' procedure. The basic steps of the complete project include: designing a method for high-quality voice transformation, a suitable algorithm in Matlab/Simulink and,finally, translating it into Digital Signal Processor target code by means of a rapid prototyping approach. The original code was developed in Matlab and so we used the Mathworks MATLAB's Real Time Workshop (RTW)DSP platform for rapid prototyping.