摘要
本文介绍了一个根据音乐的曲式和情感识别的音乐动画CAD系统。该系统上要由四部分组成。首先对乐曲的曲式特征进行识别从而将整首乐曲分成若干个乐段;然后分别对每一个乐段的情感内涵进行识别;第三,根据动画的物理模型建立基本表演程序库;最后,通过对各乐段的情感与基本表演程序库中的基本表演程序进行匹配而生成音乐动画。我们以一个音乐喷泉为动画模型对该方法进行了验证,结果是相当满意的。
In this paper, a CAD (computer aided design) system of music animation based on form and mood recognition is presented. It is composed of four parts. On the one hand, the music form is recognized to partition a piece of music into several paragraphs, then the mood of each paragraph is recognized. On the other hand, a basic performance program base is constructed based on the physical model in the animation. Finally, by matching the mood of every paragraph with a basic performance program in the basic performance program base, the music animation is generated. We evaluate this system with a model of music fountain and the result is quite satisfied.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2003年第3期283-287,共5页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金(No.60174015)
清华大学基础研究基金
关键词
计算机图形技术
曲式识别
情感识别
音乐动画
CAD系统
Music Animation, Musical Instrument Digital Interface, Form Recognition, Mcxxl Recognition, Fuzzy Systems
