面向情感的电影背景音乐分类方法

计算机科学 ›› 2013, Vol. 40 ›› Issue (12): 37-40.

面向情感的电影背景音乐分类方法

张宝印,于俊清,唐九飞,何云峰,王赠凯

华中科技大学计算机科学与技术学院武汉430074;华中科技大学计算机科学与技术学院武汉430074;华中科技大学计算机科学与技术学院武汉430074;华中科技大学计算机科学与技术学院武汉430074;华中科技大学计算机科学与技术学院武汉430074

出版日期:2018-11-16 发布日期:2018-11-16
基金资助:
本文受国家自然科学基金(61173114,60903095,61202300),湖北省杰出青年基金(2010CDA084),广东省产学研项目(2011B090400251)资助

Affective-oriented Movie Background Music Classification

ZHANG Bao-yin,YU Jun-qing,TANG Jiu-fei,HE Yun-feng and WANG Zeng-kai

Online:2018-11-16 Published:2018-11-16

摘要/Abstract

摘要： 电影背景音乐在强化电影情感、增加情节戏剧性和渲染气氛方面有不可替代的作用。如果能对电影的背景音乐进行面向情感的自动分类,将会提高电影情感内容分析的准确率。针对此问题,构造了电影背景音乐的情感特征向量与电影背景音乐情感分类器,从而改进了背景音乐片断的情感标注。电影背景音乐特征向量由从音乐音频信号中提取的小节长度节奏模式特征、小节长度低音线特征及梅尔频率倒谱系数和音程特征组成。节奏模式和低音线特征与其它特征的不同之处在于其能够反映出电影背景音乐片段的整体节奏结构。引入了概率潜在语义分析(PLSA)方法,构造了电影背景音乐情感分类器,并将电影背景音乐依据情感分为兴奋、紧张、放松和哀伤4类。实验结果表明,构造的电影背景音乐情感特征向量和引入的PLSA分类方法较之现有文献中用到的方法提高了分类的准确率。

Abstract: Movie background music plays an irreplaceable role in strengthening film affection,heightening the dramatic and rendering atmosphere．If movie background music can be automatically classified by affection,it will be remarkable to improve the accuracy of movie affective content analysis undoubtedly．In view of this,movie background music movie background music affection feature vector and classifier were proposed,so that the annotation of movie background music was improved．Movie background music affection vector is consisted of bar-long rhythm patterns,bar-long baseline patterns,Mel Frequency Cepstrum Coefficients (MFCC) and interval features extracted from music audio signal．Compared with other features,rhythm pattern and baseline pattern features are able to demonstrate rhythm structure over movie background music clip．Probability latent semantic analysis is used to classify the movie background music into excitement,tension,relaxation and sadness．Experimental results show that the movie background music affection feature vector and the PLSA classifier effectively improve the accuracy of classes than the state of the art.

张宝印, 于俊清, 唐九飞, 何云峰, 王赠凯. 面向情感的电影背景音乐分类方法[J]. 计算机科学, 2013, 40(12): 37-40. https://doi.org/

ZHANG Bao-yin, YU Jun-qing, TANG Jiu-fei, HE Yun-feng and WANG Zeng-kai. Affective-oriented Movie Background Music Classification[J]. Computer Science, 2013, 40(12): 37-40. https://doi.org/

参考文献

[1] Yang Y-H,Lin Yu-Ching,Cheng H-T,et al．Toward Multi-mo- dal Music Emotion Classification[C]∥Proceedings of the 9th Pacific Rim Conference on Multimedia．Berlin:Springer,2008:70-79
[2] Lu Qi,Chen Xiao-ou,Yang D,et al．Boosting For Multi-ModalMusic Emotion[C]∥ACM 11th International Society for Music Information Retrieval Confe-rence．2010:105-110
[3] Lin Yu-Ching,Yang Y-H,Chen H H,et al．Exploiting Genre for Music Emotion Classification[C]∥ IEEE International Confe-rence on Multimedia & Expo,New York,2009:618-621
[4] Lu Lie,Liu Dan,Zhang Hong-jiang．Automatic Mood Detection and Tracking of Music Audio Signals [J]．IEEE Transactions on Audio,Speech,and Language Processing,2006,14(1):5-18
[5] Liu Dan,Lu Lie,Zhang Hong-jiang．Automatic Music Mood Detection from Acoustic Music Data[C]∥Proceeding of International Symposium on Music Information Retrieval．2003:1-7
[6] Shi Yuan-yuan,Zhu Xuan,Kim H-G,et al．A tempo Feature viaModulation Spectrum Analysis and Its Application to Music Emotion Classification[C]∥IEEE International Conference on Multimedia and Expo,Toronto Ont.2006:1085-1088
[7] Yang Y-H,Liu Chia-Chu,Chen H H．Music Emotion Classification:A Fuzzy Approach[C]∥ACM International Conference on Multimedia．New York,2006:81-84
[8] Yang Y-H,Lin Yu-ching,Su Ya-fan,et al．Music Emotion Classification:A Regression Approach[C]∥IEEE International Conference on Multimedia and Expo．2007:208-211
[9] Schmidt E M,Trunbull D,Kim Y E．Feature Selection for Content-Based,Time-Varying Music Emotion Regression[C]∥ACM Proceedings of the International Conference on MultimediaInformation Retrieval．Mar．2010:267-273
[10] 韩纪庆,张磊,郑铁然．语音信号处理[M]．北京:清华大学出版社,2004:44-48
[11] Tzanetakis G,Essl G,Cook P．Audio Analysis Using the Discrete Wavelet Transform[C]∥Proc．of World Student Environmental Summit．Sep．2001:185-188
[12] Tsunoo E,One N,Sagayama S．Rhythm Map:Extraction of Unit Rhythmic Patterns and Analysis of Rhythmic Structure from Music Acoustic Signals[C]∥IEEE International Conference on Audio,Speech and Signal Processing．March 2009:185-188
[13] Patterson R．Spiral Detection of Periodicity and the Spiral Form of Musical Scales[M]．Psychology of Music,1986:44-61
[14] 韩纪庆,冯涛,郑贵滨,等．音频信息处理技术[M]．北京:清华大学出版社,2007:41-46
[15] Zeng Zhi,Zhang Shu-wu,Li He-ping,et al．A Novel Approach to Musical Genre Classifition Using Probabilistic Latent Semantic Analysis Model[C]∥IEEE International Conference on MultiMedia & Expo．2009:486-489
[16] Robert L C,Jitendra V D,Bezdek J C．Efficient Implementation of the Fuzzy C-means Clustering Algorithms[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(2):248-255
[17] Thayer R E.The Biopsychology of Mood and Arousal[M]．1989:10-15
[18] Chang C-C,Lin C-J．LIBSVM:a library for support vector machines[M]．2009:10-20

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed