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