Exploring tonal variations via context-dependent tone models

In this paper, we study tonal variations by training contextdependent tone models from a large speech corpus. Each model represents a tone-in-context and can output a stylized f0 pattern for it. With these tone models, it becomes tangible to investigate f0-variations with plenty of factors. Six contextual factors are investigated to describe tones in this work. We find that impact of a factor varies across tones as well as the three states of a tone. Normally, onset pitch of a tone is determined jointly by syllable position and left tone, while, the offset pitch is mainly determined by syllable position. For a neutral tone, its pitch level is mainly depended on the left tone and syllable position affects its offset pitch. Both current vowel and right tone influence the pitch level, yet their impacts are weaker than syllable position and left tone, except for T3, the low tone.