期刊文献+

基于MFCC和GMM的个性音乐推荐模型 被引量:11

Individuality Music Recommendation Model Based on MFCC and GMM
在线阅读 下载PDF
导出
摘要 提出一种基于Mel频率倒谱系数(MFCC)和高斯混合模型(GMM)的个性音乐推荐模型的建立方法.该方法采用MFCC技术提取歌曲的语音特征,并利用GMM算法生成该歌曲的模板,然后利用音乐模板库对音乐文件进行相似度计算.实验结果表明,利用该模型为用户推荐的歌曲平均准确率为90%. A personality music recommendation algorithm model based on Mel-frequency cepstrum coefficients(MFCC) and Gaussian mixture model (GMM) is provided. This method extracts MFCC from a certain song as feature parameters, and generates a template of the song using the GMM algorithm. It then gains similar songs from the music library by comparing their templates' through similarity. From the experimental result, the correct rate of the song recommendation is 90%.
出处 《北京理工大学学报》 EI CAS CSCD 北大核心 2009年第4期351-355,共5页 Transactions of Beijing Institute of Technology
基金 国家"二四二"计划项目(2005C48)
关键词 音乐推荐 MEL频率倒谱系数 高斯混合模型 music recommendation Mel-frequency cepstrum coefficient Gaussian mixture model
  • 相关文献

参考文献8

二级参考文献49

  • 1戴红霞,赵力.采用帧概率变换的与文本无关说话人识别系统的实现[J].电声技术,2004,28(9):40-42. 被引量:4
  • 2Zhang Lei,Han Jiqing,Wang Chengfa.A novel weighted likelihood measure for speech recognition under G-Force[A].7^th joint conference on information science.USA:North Carolina,2003,692-696.
  • 3T.F.Quatieri,D.A.Reynolds,G.C.O'Leary.Handset Nonlinearity Estimation with Application to Speaker Recognition[J].IEEE Trans.Speech and Audio Processing,2000,8(5):567-584.
  • 4张磊,韩纪庆,郑铁然.语音信号处理[M].北京:清华大学出版社,2004.
  • 5K.Markov.S.Nakgawa.Text-independent Speaker Recognition System Using Frame Level Likelihood Processing[R].Technical Report of IEICE,1996,SP96-17.37-44.
  • 6边祺,张学工.模式识别[M].北京:清华大学出版社,2000.
  • 7LRabiner. Fundamentals of Speech Recognition [M]. US :Prentice Hall, 1993.
  • 8DouglasA Reynolds, Richard C Rose. Robust Text-Independent Speaker Identification Using Gaussian Mixture Speaker Models [J]. IEEE Transactions on Speech andAudio Processing January 1995 ;3 ( 1 ) :72 - 83.
  • 9KR Casfleman. Digital image Processing[M]. US: Prentice Hall, 1998.
  • 10M Kearns, Y Mansour, A Y Ng. An information - theoretic analysis of hard and soft assignment methods for clustering[C ].Proceedings of the NATO Advanced Study Institute on Learning in graphical models, 1998. 495 - 520.

共引文献29

同被引文献166

  • 1黎星星,黄小琴,朱庆生.电子商务推荐系统研究[J].计算机工程与科学,2004,26(5):7-10. 被引量:46
  • 2朱淑琴,裘雪红.一种精确检测语音端点的方法[J].计算机仿真,2005,22(3):214-216. 被引量:15
  • 3柴烨,张有光.基于小波分析的雷声信号特征提取[J].电子技术应用,2007,33(5):118-120. 被引量:5
  • 4张一彬,周杰,边肇祺,郭军.基于内容的音频与音乐分析综述[J].计算机学报,2007,30(5):712-728. 被引量:18
  • 5杨行峻 迟惠生.语音信号数字处理[M].北京:电子工业出版社,1994..
  • 6Cunningham S J, Reeves N, Britland M.Ethnographic study of music information seeking[C]//Proceedings of the 2nd ACM/IEEE-CS Joint Conference on Digital Libraries, 2003.
  • 7Lee J H,Downie J S.Survey of music information needs, uses, and seeking behaviors:preliminary findings[C]//Pro- ceedings of the International Society for Music Informa- tion Retrieval, 2004.
  • 8Tzanetakis G, Cook EMusical genre classification of au- dio signals[J].IEEE Trans on Speech and Audio Process- ing, 2002,10 (5) : 293-302.
  • 9Mcennis D, Mckay C, Fujinaga I, et al.Jaudio: a feature extraction library[C]//Proceedings of the International So- ciety for Music Information Retrieval,2005.
  • 10Gouyou F, Pachet F, Delerue O.Classifying percussive sounds: a matter of zero-crossing rate?[C]//Proceedings of the COST G-6 Conference on Digital Audio Effects,2000.

引证文献11

二级引证文献61

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