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
Dalam surat ini, kami mencadangkan kaedah yang cekap untuk meningkatkan prestasi keputusan bunyi bersuara/tidak bersuara (V/UV) untuk vocoder mod boleh dipilih (SMV) 3GPP2 menggunakan model campuran Gaussian (GMM). Kami mula-mula membentangkan analisis yang berkesan bagi ciri-ciri dan kaedah pengelasan yang diterima pakai dalam SMV. Dan vektor ciri yang digunakan pada GMM kemudiannya dipilih daripada parameter SMV yang berkaitan untuk pengelasan V/UV yang cekap. Prestasi algoritma yang dicadangkan dinilai dalam pelbagai keadaan dan menghasilkan keputusan yang lebih baik berbanding kaedah konvensional SMV.
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.
Salinan
Ji-Hyun SONG, Joon-Hyuk CHANG, "Efficient Implementation of Voiced/Unvoiced Sounds Classification Based on GMM for SMV Codec" in IEICE TRANSACTIONS on Fundamentals,
vol. E92-A, no. 8, pp. 2120-2123, August 2009, doi: 10.1587/transfun.E92.A.2120.
Abstract: In this letter, we propose an efficient method to improve the performance of voiced/unvoiced (V/UV) sounds decision for the selectable mode vocoder (SMV) of 3GPP2 using the Gaussian mixture model (GMM). We first present an effective analysis of the features and the classification method adopted in the SMV. And feature vectors which are applied to the GMM are then selected from relevant parameters of the SMV for the efficient V/UV classification. The performance of the proposed algorithm are evaluated under various conditions and yield better results compared to the conventional method of the SMV.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E92.A.2120/_p
Salinan
@ARTICLE{e92-a_8_2120,
author={Ji-Hyun SONG, Joon-Hyuk CHANG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Efficient Implementation of Voiced/Unvoiced Sounds Classification Based on GMM for SMV Codec},
year={2009},
volume={E92-A},
number={8},
pages={2120-2123},
abstract={In this letter, we propose an efficient method to improve the performance of voiced/unvoiced (V/UV) sounds decision for the selectable mode vocoder (SMV) of 3GPP2 using the Gaussian mixture model (GMM). We first present an effective analysis of the features and the classification method adopted in the SMV. And feature vectors which are applied to the GMM are then selected from relevant parameters of the SMV for the efficient V/UV classification. The performance of the proposed algorithm are evaluated under various conditions and yield better results compared to the conventional method of the SMV.},
keywords={},
doi={10.1587/transfun.E92.A.2120},
ISSN={1745-1337},
month={August},}
Salinan
TY - JOUR
TI - Efficient Implementation of Voiced/Unvoiced Sounds Classification Based on GMM for SMV Codec
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2120
EP - 2123
AU - Ji-Hyun SONG
AU - Joon-Hyuk CHANG
PY - 2009
DO - 10.1587/transfun.E92.A.2120
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E92-A
IS - 8
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - August 2009
AB - In this letter, we propose an efficient method to improve the performance of voiced/unvoiced (V/UV) sounds decision for the selectable mode vocoder (SMV) of 3GPP2 using the Gaussian mixture model (GMM). We first present an effective analysis of the features and the classification method adopted in the SMV. And feature vectors which are applied to the GMM are then selected from relevant parameters of the SMV for the efficient V/UV classification. The performance of the proposed algorithm are evaluated under various conditions and yield better results compared to the conventional method of the SMV.
ER -