An analysis-by-synthesis study of Mandarin speech prosody

Author(s): Na Zhi, Daniel Hirst, Pier Marco Bertinetto, Aijun Li and Yuan Jia


In the present paper an analysis by synthesis study of mandarin speech prosody is carried out. The mandarin prosodic features are discussed from two salient perspectives, specifically: the function of prosody and the form of prosody. The symbolic representation of prosodic form with the INTSINT (INternational Transcription System for INTonation) system [1] reduces the surface complexity of a prosodic contour to a simplified model, which contains the essential information expressing the functions of speech prosody. A proposed mapping rule between the representation of prosodic function and the representation of prosodic form is discussed and further evaluated in ProZed [2, 3, 4, 5] by generating synthesized utterances. It is suggested in the study that the synthesized mandarin data derived from the prosodic coding of INTSINT symbols can not only closely mirror the melodic features of the original utterances, but also correctly express the prosodic functions of tones and the global intonation.