The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
본 연구에서는 병리학적 음성 품질 분류 성능을 향상시키기 위한 새로운 기능을 제안합니다. 이는 왜도 및 첨도와 같은 고차 통계(HOS)의 평균, 분산 및 섭동입니다. HOS 기반 특징은 GRBAS 척도로 분류된 일반, 1등급, 2등급, 3등급 음성 간에 의미 있는 차이를 보여줍니다. 기존의 특징으로는 지터, 쉬머, HNR(고조파 대 잡음비), 단시간 에너지 변화 등이 활용됩니다. 성능은 분류 및 회귀 트리(CART) 방법으로 측정됩니다. 구체적으로 기존 특성과 HOS 기반 특성을 모두 활용한 CART 기반 방법은 87.8%의 분류 정확도로 병리학적 음성 품질 측정에 유효성을 나타냅니다.
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.
부
Ji-Yeoun LEE, Sangbae JEONG, Hong-Shik CHOI, Minsoo HAHN, "Objective Pathological Voice Quality Assessment Based on HOS Features" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 12, pp. 2888-2891, December 2008, doi: 10.1093/ietisy/e91-d.12.2888.
Abstract: This work proposes new features to improve the pathological voice quality classification performance. They are the means, the variances, and the perturbations of the higher-order statistics (HOS) such as the skewness and the kurtosis. The HOS-based features show meaningful differences among normal, grade 1, grade 2, and grade 3 voices classified in the GRBAS scale. The jitter, the shimmer, the harmonic-to-noise ratio (HNR), and the variance of the short-time energy are utilized as the conventional features. The performances are measured by the classification and regression tree (CART) method. Specifically, the CART-based method by utilizing both the conventional features and the HOS-based ones shows its effectiveness in the pathological voice quality measurement, with the classification accuracy of 87.8%.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.12.2888/_p
부
@ARTICLE{e91-d_12_2888,
author={Ji-Yeoun LEE, Sangbae JEONG, Hong-Shik CHOI, Minsoo HAHN, },
journal={IEICE TRANSACTIONS on Information},
title={Objective Pathological Voice Quality Assessment Based on HOS Features},
year={2008},
volume={E91-D},
number={12},
pages={2888-2891},
abstract={This work proposes new features to improve the pathological voice quality classification performance. They are the means, the variances, and the perturbations of the higher-order statistics (HOS) such as the skewness and the kurtosis. The HOS-based features show meaningful differences among normal, grade 1, grade 2, and grade 3 voices classified in the GRBAS scale. The jitter, the shimmer, the harmonic-to-noise ratio (HNR), and the variance of the short-time energy are utilized as the conventional features. The performances are measured by the classification and regression tree (CART) method. Specifically, the CART-based method by utilizing both the conventional features and the HOS-based ones shows its effectiveness in the pathological voice quality measurement, with the classification accuracy of 87.8%.},
keywords={},
doi={10.1093/ietisy/e91-d.12.2888},
ISSN={1745-1361},
month={December},}
부
TY - JOUR
TI - Objective Pathological Voice Quality Assessment Based on HOS Features
T2 - IEICE TRANSACTIONS on Information
SP - 2888
EP - 2891
AU - Ji-Yeoun LEE
AU - Sangbae JEONG
AU - Hong-Shik CHOI
AU - Minsoo HAHN
PY - 2008
DO - 10.1093/ietisy/e91-d.12.2888
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2008
AB - This work proposes new features to improve the pathological voice quality classification performance. They are the means, the variances, and the perturbations of the higher-order statistics (HOS) such as the skewness and the kurtosis. The HOS-based features show meaningful differences among normal, grade 1, grade 2, and grade 3 voices classified in the GRBAS scale. The jitter, the shimmer, the harmonic-to-noise ratio (HNR), and the variance of the short-time energy are utilized as the conventional features. The performances are measured by the classification and regression tree (CART) method. Specifically, the CART-based method by utilizing both the conventional features and the HOS-based ones shows its effectiveness in the pathological voice quality measurement, with the classification accuracy of 87.8%.
ER -