Researchers collected almost 200 sound samples, including human and canine vocalizations, as well as environmental noises and silence.

研究人员们采集了大约200份声音样本，其中包含了人类和犬类的发音，以及环境噪音和静默时的背景声音。

Some frequency plots are also available to validate the output of the algorithm against the real-world sound samples from the lab.

论文中也提供了一些频率图，用来和实验室采集的现实世界的声音样本进行比对，从而验证算法的输出结果。

The researchers fed their recordings to artificial-intelligence models that had been trained, using sound samples from elsewhere in Ecuador, to identify 75 bird species from their calls.

研究人员将录音输入到经过训练的人工智能模型中，使用来自厄瓜多尔其他地方的声音样本，从它们的叫声中识别出 75 种鸟类。