新加坡民族音乐数据集

新加坡民族音乐数据集是由新加坡科技设计大学和国家大学新加坡合作创建，包含来自新加坡三大主要民族（华人、马来人和印度人）的音乐片段。数据集共收录15,725首歌曲，涵盖中文、马来语、印地语和泰米尔语歌曲。创建过程中，使用Spotify API手动筛选歌曲，并提取了包括260个低级特征和98个高级特征。该数据集旨在通过机器学习模型分析和预测歌曲的民族来源，未来将应用于分析新加坡国家日歌曲等典型音乐，以探索音乐的民族影响和起源。

The Singapore Ethnic Music Dataset was collaboratively created by the Singapore University of Technology and Design and the National University of Singapore. It contains music clips from the three major ethnic groups in Singapore: Chinese, Malay, and Indian. The dataset includes a total of 15,725 songs, covering tracks in Chinese, Malay, Hindi, and Tamil. During its development, songs were manually screened using the Spotify API, and 260 low-level audio features and 98 high-level audio features were extracted. This dataset is intended to analyze and predict the ethnic origin of songs via machine learning models. In the future, it will be applied to analyze representative music such as Singapore National Day songs, so as to explore the ethnic influences and origins of music.