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
Nesta carta, propomos um método aprimorado de classificação de fala/não fala para classificar efetivamente uma fonte multimídia. Para melhorar o desempenho, introduzimos um recurso baseado na análise de duração espectral e combinamos recursos recentemente propostos, como alta relação de taxa de cruzamento zero (HZCRR), baixa relação de energia de curto tempo (LSTER) e razão de pitch (PR). De acordo com os resultados de nossos experimentos com fala, música e sons ambientais, o método proposto obteve resultados de classificação elevados quando comparado com abordagens convencionais.
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
Ji-Soo KEUM, Hyon-Soo LEE, Masafumi HAGIWARA, "An Improved Speech / Nonspeech Classification Based on Feature Combination for Audio Indexing" in IEICE TRANSACTIONS on Fundamentals,
vol. E93-A, no. 4, pp. 830-832, April 2010, doi: 10.1587/transfun.E93.A.830.
Abstract: In this letter, we propose an improved speech/ nonspeech classification method to effectively classify a multimedia source. To improve performance, we introduce a feature based on spectral duration analysis, and combine recently proposed features such as high zero crossing rate ratio (HZCRR), low short time energy ratio (LSTER), and pitch ratio (PR). According to the results of our experiments on speech, music, and environmental sounds, the proposed method obtained high classification results when compared with conventional approaches.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E93.A.830/_p
Copiar
@ARTICLE{e93-a_4_830,
author={Ji-Soo KEUM, Hyon-Soo LEE, Masafumi HAGIWARA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={An Improved Speech / Nonspeech Classification Based on Feature Combination for Audio Indexing},
year={2010},
volume={E93-A},
number={4},
pages={830-832},
abstract={In this letter, we propose an improved speech/ nonspeech classification method to effectively classify a multimedia source. To improve performance, we introduce a feature based on spectral duration analysis, and combine recently proposed features such as high zero crossing rate ratio (HZCRR), low short time energy ratio (LSTER), and pitch ratio (PR). According to the results of our experiments on speech, music, and environmental sounds, the proposed method obtained high classification results when compared with conventional approaches.},
keywords={},
doi={10.1587/transfun.E93.A.830},
ISSN={1745-1337},
month={April},}
Copiar
TY - JOUR
TI - An Improved Speech / Nonspeech Classification Based on Feature Combination for Audio Indexing
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 830
EP - 832
AU - Ji-Soo KEUM
AU - Hyon-Soo LEE
AU - Masafumi HAGIWARA
PY - 2010
DO - 10.1587/transfun.E93.A.830
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E93-A
IS - 4
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - April 2010
AB - In this letter, we propose an improved speech/ nonspeech classification method to effectively classify a multimedia source. To improve performance, we introduce a feature based on spectral duration analysis, and combine recently proposed features such as high zero crossing rate ratio (HZCRR), low short time energy ratio (LSTER), and pitch ratio (PR). According to the results of our experiments on speech, music, and environmental sounds, the proposed method obtained high classification results when compared with conventional approaches.
ER -