论文部分内容阅读
在音乐分类问题中,绝大多数的算法需要提取多个特征值进行分析,工作量和复杂程度也随之增加,并且分类太绝对化.为了降低工作量和复杂程度,采用新的方式对音乐进行分类,即引进灰色关联度分析方法.现有的灰色T型关联度模型均存在不足,对序列采用绝对初值化处理,并且对关联系数计算公式进行改进,增强了结果的准确性和可信度.将提取出的短时能量、短时平均过零率和短时平均幅度作为音乐分类的三大特征值,对大部分音乐进行了较为准确的分类,排除率达到90.1%.而且此方法能够体现出各音乐之间的关联程度,使得分类更加人性化,这点具有现实意义.并且避免了复杂的计算过程和巨大的工作量,简化了解决问题的方式,也减少了对特征值的依赖,仅采用三种特征就达到了很好的效果.这充分反映了思路的正确性、实用性和可行性.
In music classification, the vast majority of algorithms need to extract multiple eigenvalues for analysis, the workload and complexity also increase, and the classification is too absolute. In order to reduce the workload and complexity, a new approach to music , The introduction of the gray correlation analysis method.Existing existing gray T-type correlation models are deficient, the absolute initial value of the sequence is used, and the calculation formula of the correlation coefficient is improved to improve the accuracy of the results Reliability.With the extracted short-time energy, short-term average zero-crossing rate and short-term average amplitude as the three eigenvalues of music classification, most of the music has been classified more accurately, with the elimination rate of 90.1% The method can reflect the correlation between the music and make the classification more humane, which is of practical significance and avoids the complicated calculation process and huge workload, simplifies the way to solve the problem and reduces the eigenvalue Of the dependence, only using three characteristics to achieve good results, which fully reflects the correctness of ideas, practicality and feasibility.