Stress detection based on multi-class probabilistic support vector machines for accented English speech

Jhing Fa Wang, Gung Ming Chang, Jia Ching Wang, Shun Chieh Lin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

A stress detection based on multi-class probabilistic support vector machines (MCP-SVMs) is proposed for classifying speech into following categories - no stress, primary stress, and secondary stress. The stress classifier is performed with a feature set including perceptual features, MFCC, delta-MFCC and delta-delta-MFCC. To observe that speakers from the same accent regions had similar tendencies in mispronunciations including word stress, this work uses English Across Taiwan (EAT) to represent Taiwanese-accented English speech corpora. The overall performance in the experimental results achieves about 84% classification of accuracy.

Original languageEnglish
Title of host publication2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009
Pages346-350
Number of pages5
DOIs
StatePublished - 2009
Event2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009 - Los Angeles, CA, United States
Duration: 31 Mar 20092 Apr 2009

Publication series

Name2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009
Volume7

Conference

Conference2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009
Country/TerritoryUnited States
CityLos Angeles, CA
Period31/03/092/04/09

Fingerprint

Dive into the research topics of 'Stress detection based on multi-class probabilistic support vector machines for accented English speech'. Together they form a unique fingerprint.

Cite this