Bengalese Finch song repository

This is a collection of song from four Bengalese finches recorded in the Sober lab at Emory University. The song has been hand-labeled by two of the authors. We share it as a means of testing different machine learning algorithms for classifying the elements of birdsong, known as syllables. A Python package, hybrid-vocal-classifier (HVC), has been tested using this dataset: https://github.com/NickleDave/hybrid-vocal-classifier. <br>The actual sound files have the extension .cbin and were collected using the program EvTAF. They can be loaded with the `load_cbin` function in the `evfuncs` module of HVC. Each .cbin file has an associated .cbin.not.mat file that contains song syllable onsets, offsets, labels, etc. These files can be opened with the `load_notmat` function in the `evfuncs` module. Each .cbin file also has associated .tmp and .rec files also created by EvTAF. Those files are not strictly required to work with this dataset but are included for completeness.<br>本数据集收录了埃默里大学索伯实验室录制的4只孟加拉雀（Bengalese finches）的鸣唱样本，其鸣唱单元已由两名作者手工标注。我们公开该数据集的初衷，是为了测试用于分类鸟鸣单元——即鸣唱音节（syllables）——的各类机器学习算法。本数据集已用于测试Python工具包hybrid-vocal-classifier（HVC），该工具包的开源地址为：https://github.com/NickleDave/hybrid-vocal-classifier。 实际的音频文件格式为.cbin，通过EvTAF软件采集获得，可通过HVC工具包中evfuncs模块的`load_cbin`函数加载。每个.cbin文件均附带一个.cbin.not.mat文件，其中存储了鸣唱音节的起始时刻、终止时刻、标注标签等信息，此类文件可通过evfuncs模块中的`load_notmat`函数读取。每个.cbin文件还附带由EvTAF生成的.tmp和.rec辅助文件；尽管使用本数据集时并非必须用到此类文件，但我们仍将其一并公开以保证数据集的完整性。