Abstract—Voice Conversion (VC) consists in modifying a source voice to a target speaker voice. In our approach, we modified only the Code excited linear Predictive (CELP) coder by introducing a pre-processing before the coder for the voice conversion. The decoder part of CELP was not modified. This allows maintaining the transmission rate. Our approach for conversion consists in separating the voiced and unvoiced frames, and thus two different conversion functions are associated. The Spectral Frequency Parameters LSF parameters are adopted to represent the vocal tract and Gaussian Mixture Models (GMM) are used to calculate the conversion functions. The pitch for the voiced frames is transformed by linear conversion. The model was tested for conversions between male and female voices. 
 

Index Terms—voice conversion, gaussian mixture model (GMM), CELP, LPC, speech coder

Cite: A. Guerid and A. Houacine, "CELP Coder Modification for the Voice Conversion," International Journal of Signal Processing Systems, Vol. 4, No. 2, pp. 124-127, April 2016. doi: 10.12720/ijsps.4.2.124-127