Mandarin Stress Detection Using Acoustic, Lexical and Syntactic Features: Mandarin Stress Detection Using Acoustic, Lexical and Syntactic Features

The stress is important to improve the naturalness,understandability and intelligibility of speech synthesis system and the correct rate of automatic speech recognition system.In this paper,we conduct stress detection by using the acoustic,lexical and syntactic features based on large scale prosodic annotation corpus.Boosting classification and regression tree is utilized to model the acoustic,lexical and syntactic features,which adequately utilizes the property of the current syllable.Conditional random fields(CRFs) are utilized to model the lexical and syntactic features,which adequately utilize the contextual property of the current syllable.The combination of boosting classification and regression tree and conditional random fields achieves better classification effect when compared with boosting classification and regression tree model or conditional random fields.The combined model overcomes the efficiency of boosting classification and regression tree model,and realizes the complementarities with the advantages of boosting classification and regression tree and conditional random fields.The experimental results indicate that the proposed method acquires better classification effect,and achieves 84.82% stress detection accuracy rate on ASCCD.Compared with the previous counterpart work in the same conditions(the same training set and testing set),there are 4.01% and 1.67% improvements respectively in terms of the correct rate.In this paper,we also compare the differences and the similarities between Mandarin stress detection and English pitch accent detection.Based on the feature analysis on the large scale prosodic annotation corporus,we also verify some linguistic conclusions in a different way.