Hainan gibbon (Nomascus hainanus) bioacoustics dataset for machine learning

Data accompanying the paper: "<strong>Empowering Deep Learning Acoustic Classifiers with Human-like Ability to Utilize Contextual Information for Wildlife Monitoring</strong>" We provide the audio data (.wav) used to test our neural network classifier along with the corresponding labelled text files (.svl). The audio and labelled files can easily be viewed in Sonic Visualiser. Drag and drop the audio file. Create the spectrogram layer. Drag and drop the corresponding .svl file. The dataset provided here is a subset of the full dataset provided here: 10.5281/zenodo.3991714. This dataset has additional files that were manually annotated, which were not manually verified in the original version (10.5281/zenodo.3991714). <strong>Files provided</strong> <strong>Audio_x.zip</strong> -- we provide x number of .zip files containing audio files, numbered 1 to 4. These were created in batches to simplify downloads. <strong>Annotations.zip -</strong>- .svl files which contain the manually verified labels. These files can be read in Sonic Visualiser, or as .XML files in a programming language. We took care to annotate the start and stop time of each gibbon call. The height of each bounding box is not important as the frequency range of Hainan gibbons is already known. <strong>model_weights_tensorflow.hdf5 </strong>-- the Tensorflow model. Load the model using: model = tf.keras.models.load_model(model_filepath) note that the model expects a three channel input as explained in the research article.本数据集配套于论文：<strong>《赋能深度学习声学分类器具备类人上下文信息利用能力以服务野生动物监测》</strong>。我们提供了用于测试本研究神经网络分类器的音频数据（.wav格式）与对应带标注的文本文件（.svl格式）。音频与标注文件可通过Sonic Visualiser便捷查看：拖入音频文件创建频谱图图层，再拖入对应的.svl格式文件即可完成加载。本数据集为下述完整数据集的子集：10.5281/zenodo.3991714。相较于原始版本（10.5281/zenodo.3991714），本数据集额外包含经人工标注的文件，而原始版本中的对应文件未经过人工核验。<strong>提供的文件</strong> <strong>Audio_x.zip</strong>：我们提供了编号为1至4的音频压缩包，按批次打包以简化下载流程，包内存储音频文件。 <strong>Annotations.zip</strong>：内含经人工核验的.svl格式标注文件。此类文件可通过Sonic Visualiser读取，也可作为XML文件在编程语言中解析。我们已对每只长臂猿鸣叫的起止时间进行了精准标注。由于海南长臂猿的频率范围已为学界熟知，因此边界框的高度无需特别在意。 <strong>model_weights_tensorflow.hdf5</strong>：TensorFlow模型权重文件。可通过以下代码加载该模型：`model = tf.keras.models.load_model(model_filepath)`，需注意该模型要求三通道输入，具体说明可参阅研究论文。