期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于MFCC和加权动态特征组合的环境音分类 被引量：4

Environmental Sounds Classification Using MFCC Combined with Weighted Dynamic Features
在线阅读 下载PDF
导出
摘要 提出了基于Mel倒谱系数和加权的一阶、二阶差分Mel倒谱系数特征参数组合的环境音分类,实验结果表明以MFCC+αΔMFCC+βΔΔMFCC为特征参数的分类正确率明显高于MFCC、MFCC+ΔMFCC和MFCC+ΔMFCC+ΔΔMFCC。 This paper presents environmental sounds classification using MFCC combined with weighted delta Mel-Frequeney Cepstrum Coefficient （△MFCC） and double delta Mel-Frequeney Cepstrum Coefficient（△△MFCC）. Experiment results show that MFCC＋α△MFCC-β△△MFCC yields higher recognition accuracy for environmental sounds.
作者 魏丹芳 李应
机构地区 福州大学数学与计算机科学学院
出处 《计算机与数字工程》 2010年第2期7-10,共4页 Computer & Digital Engineering
基金 福建省教育厅项目(编号:JA09021)资助
关键词 MEL倒谱系数 差分Mel倒谱系数 环境音分类 mel-frequency cepstrum coefficient, delta mel-frequency cepstrum coefficient, environmental sounds classificaition
分类号 TN912.3 [电子电信—通信与信息系统]
  • 相关文献

参考文献6

  • 1Zhang T, Kuo C C C. Audio content analysis for online audiovisual data segmentation and classification [J]. IEEE Transactions on Speech and Audio Processing, 2001,9(4) : 441-458.
  • 2Kim K M, Kim S Y, Jeon J K, et al. Quick audio retrieval using multiple feature vectors[J]. IEEE Trans. on Consumer Electronics, 2006,52 (1) : 200-205.
  • 3Kiranyaz S, Qureshi A F, Gabbouj M A generic audioctassification and segmentation approach for multimedia indexing and retrieval[J]. IEEE Trans. on Audio, Speech and Language Processing,2006,14(3):1062-1081.
  • 4Ying Li. A Quick Classification for Area Environmental Audio Data Based on Local Search Tree[J]. ESIAT 2009.
  • 5江星华,李应.基于LPCMCC的音频数据检索方法[J].计算机工程,2009,35(11):246-247. 被引量：5
  • 6于明,袁玉倩,董浩,王哲.一种基于MFCC和LPCC的文本相关说话人识别方法[J].计算机应用,2006,26(4):883-885. 被引量：14

二级参考文献9

  • 1张成,蒋皓石,林嘉宇.基于16位单片机的语音电子门锁系统[J].电子技术应用,2005,31(7):18-21. 被引量：9
  • 2Wold E, Blum T, Keislar D, et al. Content-based Classification, Serarch, and Retrieval of Audio[J]. IEEE Multimedia, 1996, 3(3): 27-36.
  • 3Li S Z. Content-based Classification and Retrieval of Audio Using the Nearest Feature Line Method[J]. IEEE Trans. on Speech and Audio Processing, 2000, 8(5): 619-625.
  • 4Kim K M, Kim S Y, Jeon J K, et al. Quick Audio Retrieval Using Multiple Feature Vectors[J]. IEEE Trans. on Consumer Electronics, 2006, 52(1): 200-205.
  • 5Zhang Xueying, Guo Yueling, Hou Xuemei. A Speech Recognition Method of Isolated Words Based on Modified LPC Cepstrum[C]//Proc. of GrC'07. California, USA: IEEE Press, 2007.
  • 6何英 何强.MATLAB扩展编程[M].北京：清华大学出版社,2002..
  • 7FAKOTAKIS N,SIRIGOS J.A high performance text-independent speaker identification system based on vowel spotting and neural nets[A].Proceedings of IEEE Int Conf on Acoustics,Speech and Signal Processing[C].Atlanta,GA,USA,1996.
  • 8林宝成,陈永彬.基于ARMA模型的汉语讲话者识别[J].声学学报,1998,23(3):229-234. 被引量：6
  • 9付强,易克初,田斌,田红心.一种采用余弦镶边临界带滤波器组的弯折谱失真测度[J].西安电子科技大学学报,1999,26(6):823-827. 被引量：6

共引文献17

同被引文献42

  • 1章熙春,曹燕,张军,韦岗.语音MFCC特征计算的改进算法[J].数据采集与处理,2005,20(2):161-165. 被引量：7
  • 2郭春霞,裘雪红.基于MFCC的说话人识别系统[J].电子科技,2005,18(11):53-56. 被引量：19
  • 3陈芬菲.基于GMM的说话人识别系统[J].微处理机,2006,27(4):76-77. 被引量：3
  • 4Twang Y, Li B, Jiang X Q, et al. Speaker Recognition Based on Dynamic MFCC Parameters[ C ]//International Conferenceon Image Analysis and Signal Processing. [ s. 1. ] : [ s. n. ], 2009:406-409.
  • 5l_,ai Y P, Siu M H, Mark B. Joint Optimization of the Frequency Domain and Time-domain Transformation in Deriving Gener- allized Static and Dynamic MFCCs [ J ]. IEEE Signal Process- ing Letters ,2006,13 ( 11 ) :707-710.
  • 6Wang C, Miao Z J, Meng X. Differential MFCC and Vector Quantization Used for Real-time Speaker Recognition System [ J ]. Congress on Image and Signal Processing,2008 (5) :319 -323.
  • 7Dempster A, Laird N, Rubin D. Maximum likelihood from in- complete data via the EM algorithm [ J ]. J Royal Stat Soc, 1977,39( 1 ) : 1-38.
  • 8Choi W-H, Kim S-I, Keum M-S, et al. Acoustic and visu- al signal based context awareness system for mobile appli- cation[ J ]. IEEE Transactions on Consumer Electronics, 2011,57(2) :738-746.
  • 9Ma Ling, Milner B, Smith D. Acoustic environment classi- fication[ J ]. ACM Transactions on Speech and Language Processing, 2006,3 (2).
  • 10Wichern G, Xue Jiachen, Thornburg H, et al. Segmenta- tion, indexing, and retrieval for environmental and natural sounds [ J ]. IEEE Transactions on Audio, Speech, and Language Processing, 2010,18 (3) :688-707.

引证文献4

二级引证文献16

计算机与数字工程
2010年 第2期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部