This paper proposes prosodic unit based segmentation for prosody evaluation by using pitch accent detection and forced alignment techniques. Support Vector Machine (SVM) is used to evaluate the prosody of non-native English speakers without reference utterances. Experimental results show the superiority of prosodic unit segmentation over word segmentation in terms of classification accuracy and dimension of the feature vectors used by SVM.
Sixuan ZHAO
Nanyang Technological University
Soo Ngee KOH
Nanyang Technological University
Kang Kwong LUKE
Nanyang Technological University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Sixuan ZHAO, Soo Ngee KOH, Kang Kwong LUKE, "Reference-Independent Prosody Evaluation Based on Prosodic Unit Segmentation" in IEICE TRANSACTIONS on Information,
vol. E96-D, no. 9, pp. 2143-2146, September 2013, doi: 10.1587/transinf.E96.D.2143.
Abstract: This paper proposes prosodic unit based segmentation for prosody evaluation by using pitch accent detection and forced alignment techniques. Support Vector Machine (SVM) is used to evaluate the prosody of non-native English speakers without reference utterances. Experimental results show the superiority of prosodic unit segmentation over word segmentation in terms of classification accuracy and dimension of the feature vectors used by SVM.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.2143/_p
Copy
@ARTICLE{e96-d_9_2143,
author={Sixuan ZHAO, Soo Ngee KOH, Kang Kwong LUKE, },
journal={IEICE TRANSACTIONS on Information},
title={Reference-Independent Prosody Evaluation Based on Prosodic Unit Segmentation},
year={2013},
volume={E96-D},
number={9},
pages={2143-2146},
abstract={This paper proposes prosodic unit based segmentation for prosody evaluation by using pitch accent detection and forced alignment techniques. Support Vector Machine (SVM) is used to evaluate the prosody of non-native English speakers without reference utterances. Experimental results show the superiority of prosodic unit segmentation over word segmentation in terms of classification accuracy and dimension of the feature vectors used by SVM.},
keywords={},
doi={10.1587/transinf.E96.D.2143},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - Reference-Independent Prosody Evaluation Based on Prosodic Unit Segmentation
T2 - IEICE TRANSACTIONS on Information
SP - 2143
EP - 2146
AU - Sixuan ZHAO
AU - Soo Ngee KOH
AU - Kang Kwong LUKE
PY - 2013
DO - 10.1587/transinf.E96.D.2143
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2013
AB - This paper proposes prosodic unit based segmentation for prosody evaluation by using pitch accent detection and forced alignment techniques. Support Vector Machine (SVM) is used to evaluate the prosody of non-native English speakers without reference utterances. Experimental results show the superiority of prosodic unit segmentation over word segmentation in terms of classification accuracy and dimension of the feature vectors used by SVM.
ER -