MIDI文件主旋律音轨的抽取

在数字音乐的研究应用中,大多数高层语义的音乐特征研究都以MIDI音乐文件库作为素材,其中主旋律音轨作为最重要的音乐信息,而从MIDI文件中获取主旋律信息具有很大的难度和误差.提出一种应用随机森林的方法自动抽取MIDI文件中主旋律所在的音轨.首先根据信息熵理论定义了音轨特征的熵值,并通过实验判断该特征的熵值对区分MIDI主旋律音轨与伴奏音轨是有效的.然后由MIDI文件的音轨信息熵和一些其他重要特征组成特征向量,构建随机森林分类器抽取MIDI文件主旋律所在的音轨.由实验可知,该模型有较高的准确率,对提取MIDI文件主旋律音轨有效.     

音乐情感的自动识别

音乐与情感有着非常密切的联系,发展针对音乐的情感识别系统,对于计算机音乐的研究与发展有着深远的意义.提出了一种基于PAD(Pleasure arousal dominance)模型以及基因表达式编程(GEP)算法的音乐情感自动识别方法.在众多音乐特征元素中抽取与情感关系密切的6个特征,并且采用PAD模型来描述音乐中的情感,在此基础上使用GEP算法实现对简单乐曲中单一情感的自动识别.从实验结果分析,本系统能够达到一个比较理想的识别效果和较低的识别误差.     

Auto Composition System for Two Voice Part Inventions Based on Soft Computational Methods

Algorithmic composition is a very popular research field today. Bach's "two voice part invention" is the research object in this.paper. The grammar and compositional rules of "invention" are introduced first, Then two soft computational methods, genetic algorithms and back propagation (BP) neural network technology,are combined to the experiment on assisting in composing "two voice part inventions ". The system presented in this paper is quite effective and satisfactory.     

Interpretation Method of Guqin （Chinese Ancient Zither ） Notation Based on Radical and Structural Analysis

Guqin music is a precious cultural heritage of China. The notation of Guqin is very special, which records its playing methods and techniques. For the purpose of preserving the guqin art, the digitalization of guqin notation and an interpretation method of guqin notation were conducted. By using this interpretation method, raw images of handwritten notations are transformed into structural data that can be processed and analyzed by computers easily. The method decomposes each single complex character of guqin notations into simple radicals and finds the structure of the character. According to the radicals and the structure, the character is interpreted into meaningful codes. The experimental results show our method is effective.