摘要
《机器人与机器学习每日新闻》的一位新闻记者兼新闻编辑发表了关于应用数学和非线性科学的新研究成果。根据NewsRx记者从中国三亚发回的新闻报道，研究表明：“随着现代信息技术的不断发展，智能音频处理技术与声乐教学的结合逐渐成为研究的热点。”本文首先构建了基于音乐情感和乐器识别的声乐教学系统，利用PSO算法优化支持向量机，构建了基于SVM的音乐情感识别和乐器识别方法，通过对不同音乐情感识别模型和乐器识别模型的对比实验，探讨了本文模型在音乐情感识别和乐器识别方面的性能，并通过多目标比例积分微分算法对声乐教学系统进行控制和优化。对声乐教学系统的应用效果进行了分析,结果表明,采用PSO优化的SVM模型对情感识别有较好的效果,识别准确率比对比模型提高16.67%,平均适应性为70%~90%。该模型的仪器识别率分别为18.17%和7.45%。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – New study results on applied mathematics and nonl inear sciences have been published. According to news reporting from Sanya, Peop le’s Republic of China, by NewsRx journalists, research stated, “With the contin uous development of modern information technology, the combination of intelligen t audio processing technology and vocal music teaching has gradually become a re search hot spot.” The news editors obtained a quote from the research from Sanya University: “In t his paper, we first build a vocal music teaching system based on music emotion a nd instrument recognition, optimize the support vector machine using the PSO alg orithm, construct the music emotion recognition and instrument recognition metho d based on SVM, and control and optimize the vocal music teaching system through multi-objective proportional integral differentiation algorithm. Through the co mparison experiments of different models of music emotion recognition and musica l instrument recognition, the performance of music emotion recognition and music al instrument recognition of this paper’s model is explored. Then, the applicati on effect analysis of the vocal music teaching system is carried out. The result s show that the SVM model optimized by PSO has a more satisfactory effect on mus ic emotion recognition, with a recognition accuracy 16.67% higher than the comparison model and an average adaptability of 70%-90% . In addition, this model has a higher instrument recognition rate of 18.17% and 7.45% compared to the other two models.”
NETL
NSTL