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
Propomos um método eficaz de identificação de gênero baseado em voz usando uma máquina de vetores de suporte (SVM). O SVM é um algoritmo de classificação binária que classifica dois grupos encontrando o limite não linear voluntário em um espaço de recursos e é conhecido por produzir alto desempenho de classificação. No presente trabalho, comparamos o desempenho de identificação do SVM com o de um método baseado em modelo de mistura gaussiana (GMM) usando os coeficientes cepstrais de frequência mel (MFCC). Uma nova abordagem de incorporação de um esquema de fusão de características baseado em uma combinação do MFCC e da frequência fundamental é proposta com o objetivo de melhorar o desempenho da identificação de gênero. Os resultados experimentais demonstram que o desempenho da identificação de género utilizando o SVM é significativamente melhor do que o do esquema baseado no GMM. Além disso, o desempenho é substancialmente melhorado quando a técnica de fusão de recursos proposta é aplicada.
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.
Copiar
Kye-Hwan LEE, Sang-Ick KANG, Deok-Hwan KIM, Joon-Hyuk CHANG, "A Support Vector Machine-Based Gender Identification Using Speech Signal" in IEICE TRANSACTIONS on Communications,
vol. E91-B, no. 10, pp. 3326-3329, October 2008, doi: 10.1093/ietcom/e91-b.10.3326.
Abstract: We propose an effective voice-based gender identification method using a support vector machine (SVM). The SVM is a binary classification algorithm that classifies two groups by finding the voluntary nonlinear boundary in a feature space and is known to yield high classification performance. In the present work, we compare the identification performance of the SVM with that of a Gaussian mixture model (GMM)-based method using the mel frequency cepstral coefficients (MFCC). A novel approach of incorporating a features fusion scheme based on a combination of the MFCC and the fundamental frequency is proposed with the aim of improving the performance of gender identification. Experimental results demonstrate that the gender identification performance using the SVM is significantly better than that of the GMM-based scheme. Moreover, the performance is substantially improved when the proposed features fusion technique is applied.
URL: https://global.ieice.org/en_transactions/communications/10.1093/ietcom/e91-b.10.3326/_p
Copiar
@ARTICLE{e91-b_10_3326,
author={Kye-Hwan LEE, Sang-Ick KANG, Deok-Hwan KIM, Joon-Hyuk CHANG, },
journal={IEICE TRANSACTIONS on Communications},
title={A Support Vector Machine-Based Gender Identification Using Speech Signal},
year={2008},
volume={E91-B},
number={10},
pages={3326-3329},
abstract={We propose an effective voice-based gender identification method using a support vector machine (SVM). The SVM is a binary classification algorithm that classifies two groups by finding the voluntary nonlinear boundary in a feature space and is known to yield high classification performance. In the present work, we compare the identification performance of the SVM with that of a Gaussian mixture model (GMM)-based method using the mel frequency cepstral coefficients (MFCC). A novel approach of incorporating a features fusion scheme based on a combination of the MFCC and the fundamental frequency is proposed with the aim of improving the performance of gender identification. Experimental results demonstrate that the gender identification performance using the SVM is significantly better than that of the GMM-based scheme. Moreover, the performance is substantially improved when the proposed features fusion technique is applied.},
keywords={},
doi={10.1093/ietcom/e91-b.10.3326},
ISSN={1745-1345},
month={October},}
Copiar
TY - JOUR
TI - A Support Vector Machine-Based Gender Identification Using Speech Signal
T2 - IEICE TRANSACTIONS on Communications
SP - 3326
EP - 3329
AU - Kye-Hwan LEE
AU - Sang-Ick KANG
AU - Deok-Hwan KIM
AU - Joon-Hyuk CHANG
PY - 2008
DO - 10.1093/ietcom/e91-b.10.3326
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E91-B
IS - 10
JA - IEICE TRANSACTIONS on Communications
Y1 - October 2008
AB - We propose an effective voice-based gender identification method using a support vector machine (SVM). The SVM is a binary classification algorithm that classifies two groups by finding the voluntary nonlinear boundary in a feature space and is known to yield high classification performance. In the present work, we compare the identification performance of the SVM with that of a Gaussian mixture model (GMM)-based method using the mel frequency cepstral coefficients (MFCC). A novel approach of incorporating a features fusion scheme based on a combination of the MFCC and the fundamental frequency is proposed with the aim of improving the performance of gender identification. Experimental results demonstrate that the gender identification performance using the SVM is significantly better than that of the GMM-based scheme. Moreover, the performance is substantially improved when the proposed features fusion technique is applied.
ER -