Study of Prominence Detection Based on Various Phone-Specific Features

Sung Soo KIM  Chang Woo HAN  Nam Soo KIM  

IEICE TRANSACTIONS on Information and Systems   Vol.E93-D   No.8   pp.2327-2330
Publication Date: 2010/08/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E93.D.2327
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Speech and Hearing
prominence,  phone-specific,  SVM,  ANN,  Adaboost,  

Full Text: PDF(146.4KB)>>
Buy this Article

In this letter, we present useful features accounting for pronunciation prominence and propose a classification technique for prominence detection. A set of phone-specific features are extracted based on a forced alignment of the test pronunciation provided by a speech recognition system. These features are then applied to the traditional classifiers such as the support vector machine (SVM), artificial neural network (ANN) and adaptive boosting (Adaboost) for detecting the place of prominence.