Mandarin stress detection using hierarchical model based boosting classification and regression tree

Automatic stress detection is important for both speech understanding and natural speech synthesis. In this paper, we develop hierarchical model based boosting classification and regression tree (CART) to detect Mandarin stress by using acoustic evidence and text information. When comparing with previous proposed method at the same training and test sets, there are 2.52% and 1.09% absolute accuracy rate improvements respectively. We also analyze the differences between Mandarin stress detection and English pitch accent prediction, and prove some linguistic conclusions based on the large corpus in a different way.