Speaker-specific pitch contour modeling and modification

This paper describes new techniques for modeling and generating speaker-dependent pitch contours for sentences. Speech synthesis applications could generally benefit from such speaker-specific pitch contours. The proposed algorithms begin with an existing pitch contour for an utterance and use data from training utterances to modify the contour to be appropriate for a second speaker. One approach modifies the original pitch values to statistically match the desired speaker at each point in time. A second novel approach uses dynamic time warping (DTW) to select a new pitch contour from a pre-determined code book and time-align the chosen contour to the original sentence. Such contour mapping can transfer one speaker´s natural pitch characteristics to another person´s speech. Informal listener evaluations suggest that while shifting the frequency range of the original pitch contour yields some improvement, better results are obtained by applying DTW techniques to time-warp the contour from an existing sentence produced by the desired speaker