首页 | 本学科首页   官方微博 | 高级检索  
     

有效的基于内容的音频特征提取方法
引用本文:郑继明,魏国华,吴渝.有效的基于内容的音频特征提取方法[J].计算机工程与应用,2009,45(12):131-133.
作者姓名:郑继明  魏国华  吴渝
作者单位:1.重庆邮电大学 应用数学研究所,重庆 400065 2.重庆邮电大学 计算机科学与技术学院,重庆 400065
基金项目:重庆市教委科学技术研究项目 
摘    要:音频特征提取是音频分类的基础,好的特征将会有效提高分类精度。在提取频域特征Mel频率倒谱系数(MFCC)的同时,对每一帧信号做离散小波变换,提取小波域特征,把频域和小波域特征相结合计算其统计特征。通过SVM模型建立音频模板,对纯语音、音乐及带背景音乐的语音进行分类识别,取得了较高的识别精度。

关 键 词:特征提取  小波变换  Mel频率倒谱系数  支持向量机
收稿时间:2008-3-3
修稿时间:2008-6-6  

New effective method on content based audio feature extraction
ZHENG Ji-ming,WEI Guo-hua,WU Yu.New effective method on content based audio feature extraction[J].Computer Engineering and Applications,2009,45(12):131-133.
Authors:ZHENG Ji-ming  WEI Guo-hua  WU Yu
Affiliation:1.Institute of Applied Mathematics,Chongqing University of Posts and Telecommunications,Chongqing 400065,China 2.Institute of Computer Science and Technology,Chongqing University of Posts and Telecommunications,Chongqing 400065,China
Abstract:Feature extraction is the foundation of the audio classification,and good features will enhance the classification accuracy effectively.In this paper,Mel-frequency cepstrum coefficients are extracted from frequency domain of audio.At the same time, features are extracted from wavelet domain after discrete wavelet transform is done for each frame of the audio.Then the features from the frequency domain and wavelet domain are combined to calculate the statistical features.Finally,audio template is established...
Keywords:feature extraction  wavelet transform  Mel-Frequency Cepstrum Coefficients(MFCC)  Support Vector Machine(SVM)
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《计算机工程与应用》浏览原始摘要信息
点击此处可从《计算机工程与应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号