A MULTILEVEL FRAMEWORK TO MODEL THE INHERENTLY CONFOUNDING NATURE OF SENTENTIAL F0 CONTOURS FOR RECOGNIZING CHINESE LEXICAL TONES

摘要

This paper presents a multilevel framework to cope with the complex variations in Chinese sentential F0 contours in order to recognize lexical tones. Tone nucleus model is to get rid of the influence of intrinsic F0 transition loci at sub-syllable level. Pitch anchoring concept is used to normalize tonal F0 contours at syllable level. Hypo- and Hyper- intonation model is to account for the interplay of tone coarticulation and higher level prosodic effects. The whole approach achieved significant higher performance than the conventional method.