摘要
由一名新闻记者兼机器人与机器学习每日新闻编辑-调查人员讨论技术方面的新发现。根据NewsRx记者来自印度阿萨姆邦的新闻报道，研究表明，“使用计算技术对乐器进行分类是一项非常具有挑战性的任务。”新闻记者从迪布鲁加尔大学的研究中获得一句话：“信号处理和数据挖掘技术的发展，使得分析音乐信号的多种特征成为可能，这对于解决音乐分类问题至关重要。本文选取了12种流行的阿萨姆民族乐器进行鉴定，播放了12种乐器并录制了音频样本。”利用决策树分类器(DTC)、支持向量机(SVM)和线性判别分析(LDA)三种常用的分类技术对这些仪器进行了识别,并对这三种分类器进行了性能比较,所提出的特征集使DTC、SVM和LDA模型的平均准确率达到86.9%。分别为90%和92.2%。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators discuss new findings in technology. According to news reporting originating from Assam, India, by NewsRx correspondents, research stated, “The classification of musical instruments by using a computational technique is a very challenging task.” The news correspondents obtained a quote from the research from Dibrugarh Univer sity: “The developments in signal-processing and data-mining techniques have mad e it feasible to analyse the many musical signal characteristics, which is essen tial for resolving the classification issues in music. In this work, 12 popular Assamese folk music instruments were selected for identification. Twelve musicia ns played the instruments and audio samples were recorded, different instantaneo us features were extracted, and an effort has been made to identify those instru ments using three popular classification techniques - Decision Tree Classifier ( DTC), Support Vector Machine (SVM), and Linear Discriminant Analysis (LDA). A pe rformance-based comparison was made among the three classifiers. The proposed se ts of features enabled the DTC, SVM and LDA models to achieve average accuracy r atings of 86.9%, 90% and 92.2% respecti vely.”
NETL
NSTL