Speaker Transformation Using Quadratic Surface Interpolation

Speaker transformation is a technique that modifies a source speaker’s speech to be perceived as if a target speaker has spoken it. Compared to statistical techniques, warping function based transformation techniques require less training data and time. The objective of this paper is to investigate the transformation using quadratic surface interpolation. Source and target utterances were analyzed using harmonic plus noise model (HNM) and harmonic magnitudes were converted to line spectral frequencies (LSFs). Transformation function was found using LSFs of the time aligned source and target frames using dynamic time warping. The transformed LSFs were converted back to harmonic magnitudes for HNM synthesis. This method was able to transform speech with satisfactory quality. Further, the results were better if pitch frequency was included in the frame vectors.