Detection of malay phrase breaks using energy and duration

• Published in: International Journal of Simulation: Systems, Science and Technology
• Main Author: Mohamed Hanum H.; Abu Bakar Z.
• Format: Article
• Language: English
• Published: UK Simulation Society 2016
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85006056588&doi=10.5013%2fIJSSST.a.17.32.26&partnerID=40&md5=964fff492a5f38135a59d497365dd8d7

A simpler approach to identify and classify phrase breaks in prosodic phrasing using energy patterns and duration is useful in speech segmentation. Prosodic phrasing is useful to segment lengthy spontaneous speech into smaller meaningful utterance without analysis of linguistic information. We propose a listening test that allow trained listener to classify the boundaries as minor or major breaks. This cheaper and faster approach is proven useful for under-resource language such as Malay which do not have comprehensive prosodic-annotated corpus. Word-related energy and duration features are extracted from the targeted phrase breaks. The training feature set is developed from evaluation of targeted phrase break from 100 sentences evaluated in the listening test. Evaluation of the features with RBF, MLP and logistics models reveal best detection accuracy of 80.6% which is comparable to existing context-based algorithm. Instead of labeling the phrase break using linguistic and phonetic meaning, the proposed listening test allows labeling of phrase break as perceived by listener. In addition, the results can be use as preliminary information for evaluation of boundary salience at the targeted boundary locations. © 2016, UK Simulation Society. All rights reserved.