Automated identification of chicken distress vocalisations using deep learning models

Abstract The annual global production of chickens exceeds 25 billion birds, which are often housed in very large groups, numbering thousands. Distress calling triggered by various sources of stress has been suggested as an “iceberg indicator” of chicken welfare. However, to date, the identification of distress calls largely relies on manual annotation, which is very labour-intensive and time-consuming. Thus, a novel convolutional neural network-based model, light-VGG11, was developed to automatically identify chicken distress calls using recordings (3,363 distress calls and 1,973 natural barn sounds) collected on an intensive farm. The light-VGG11 was modified from VGG11 with significantly fewer parameters (9.3 million vs 128 million) and 55.88% faster detection speed while displaying comparable performance, i.e., precision (94.58%), recall (94.89%), F1-score (94.73%), and accuracy (95.07%), therefore more useful for model deployment in practice. To additionally improve light-VGG11’s performance, we investigated the impacts of different data augmentation techniques (i.e., time masking, frequency masking, mixed spectrograms of the same class, and Gaussian noise) and found that they could improve distress calls detection by up to 1.52%. Furthermore, a distress call detection demonstration on continuous audios exhibited our research’s potential for developing technologies to monitor the output of distress calls in large, commercial chicken flocks. Methods Recordings were collected in production facilities owned by Lengfeng Poultry Ltd., in Guangxi province, People’s Republic of China, between November and December 2017 and in November 2018. Chickens (mix of Chinese “spotted” and “three-yellow” breeds) were kept in stacked cages (three cages per stack, with 13-20 individuals per cage), with approximately 2,000 to 2,500 birds per house. The microphone was positioned approximately two meters up from the floor, mounted on the top cage of a stack in the middle of the barn. This placement was chosen to ensure that the recording devices did not interfere with the farm staff cleaning and maintaining the barns. All recordings were sampled at 22.05 kHz with a 16-bit bit-depth throughout the natural lifecycle (0 – 35 days) of chickens using a portable recorder (Zoom H4n Pro, Zoom Corporation, Tokyo, Japan). These recordings were collected from two different chicken flocks at the same farm, one of which was used as the development dataset to learn the model, and the other was used as a continuous testing dataset to verify the model’s generalisation capability.摘要：全球鸡肉年产量超250亿只，这类家禽通常以数千只的大规模群体饲养。由多种应激源触发的鸡只应激鸣叫，被认为是评估鸡只福利的“冰山指示器”。但截至目前，应激鸣叫的识别主要依赖人工标注，不仅劳动强度大且耗时耗力。为此，本研究开发了一种基于卷积神经网络（Convolutional Neural Network）的新型模型——轻量型VGG11（light-VGG11），利用集约化养殖场采集的音频数据（含3363条应激鸣叫与1973条鸡舍自然环境音）实现鸡只应激鸣叫的自动识别。该轻量型VGG11由经典VGG11改造而来，参数规模大幅缩减（930万 vs 1.28亿），检测速度提升55.88%，同时保持了相当的性能：精确率94.58%、召回率94.89%、F1值94.73%、准确率95.07%，因此更适合实际部署应用。为进一步提升轻量型VGG11的性能，本研究探究了不同数据增强技术（即时域掩蔽、频域掩蔽、同类语谱图混合、高斯噪声）的影响，发现这些技术可将应激鸣叫检测性能提升最高达1.52%。此外，针对连续音频的应激鸣叫检测演示验证了本研究在开发大规模商业鸡群应激鸣叫监测技术方面的应用潜力。 方法：本研究的音频数据采集于2017年11—12月及2018年11月，采集地点为中国广西壮族自治区冷丰家禽有限公司（Lengfeng Poultry Ltd.）的养殖设施。试验鸡只采用中国“麻斑”（spotted）与“三黄”（three-yellow）品种的混合群体，饲养于层叠式笼养系统中（每堆叠3笼，每笼饲养13—20只鸡只），每栋鸡舍约饲养2000—2500只鸡。麦克风安装于鸡舍中部堆叠组的顶层笼架上，距地面约2米，该安装位置可避免录音设备干扰养殖场人员对鸡舍的清洁与维护工作。本研究全程采用便携式录音机（Zoom H4n Pro，日本东京Zoom株式会社出品），以22.05kHz采样率、16位量化深度，采集鸡只整个自然生长周期（0—35日龄）的音频数据。数据采集覆盖该养殖场的两个不同鸡群：其中一个鸡群的音频数据用作模型开发的开发数据集，另一个鸡群的连续音频数据用作测试数据集以验证模型的泛化能力。