北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2006, Vol. 29 ›› Issue (s2): 35-40.doi: 10.13190/jbupt.2006s2.35.316

• 论文 • 上一篇    下一篇

音乐情感的语言值计算模型研究

孙守迁1,2 ,王鑫1 刘 涛1 汤永川1   

  1. 1.浙江大学 计算机科学与技术学院, 杭州 310027, 2.湖北工业大学 数字化艺术与设计研究中心, 武汉 430070
  • 收稿日期:2006-09-05 修回日期:1900-01-01 出版日期:2006-11-30 发布日期:2006-11-30
  • 通讯作者: 孙守迁

Study on Linguistic Computing for Music Emotion

SUN Shou-qian1,2,Wang Xin1,LIU Tao1, TANG Yong-chuan1   

  1. 1. College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China; 2 Center of Digital Art and Design, Hubei University of Technology, Wuhan 430070,China
  • Received:2006-09-05 Revised:1900-01-01 Online:2006-11-30 Published:2006-11-30
  • Contact: SUN Shou-qian

摘要:

基于音乐情感的心理模糊量的言词研究成果——Hevner情感环模型,提出了一种音乐情感的语言值计算模型。该模型利用八维语言值向量来表示音乐情感,并定义了任意两首乐曲之间的情感相似性度量。本文还通过语义认知实验建立了由基本语言值集构成的情感心理空间。结合情感化音乐检索和多专家决策的需要,本文基于音乐情感向量的代数和逻辑运算法则实现了多源情感信息的融合,实例表明该融合方法符合音乐情感认知的心理模式。

关键词: 情感认知, Hevner情感环, 音乐情感向量, 语言信息融合

Abstract:

A model for music affective computing based on Hevner affective ring—a famous psychology model for emotion representation was proposed. A 8-dimensional vector of linguistic labels is used to represent the emotion embodied in underlying music. And a new method is introduced to measure the emotion similarity between any two pieces of music. And then, the emotional space based on a set of basic linguistic labels is established via an experiment. Considering the requirements of emotional music retrieval and multi-expert decision, a linguistic information fusion method for music emotions based was presented on the arithmetic and logic operations on the emotional space, and the examples show that our model agrees with psychological pattern of the music recognition well and truly.

Key words: emotion cognition, Hevner affective ring, music affective vector, linguistic information fusion

中图分类号: