This paper presents Soundbay, an open-source Python framework that allows bio-acoustics and machine learning researchers to implement and utilize deep learning-based algorithms for acoustic audio analysis. Soundbay provides an easy and intuitive platform for applying existing models on one's data or creating new models effortlessly. One of the main advantages of the framework is the capability to compare baselines on different benchmarks, a crucial part of emerging research and development related to the usage of deep-learning algorithms for animal call analysis. We demonstrate this by providing a benchmark for cetacean call detection on multiple datasets. The framework is publicly accessible via https://github.com/deep-voice/soundbay

翻译：本文介绍了Soundbay，一个开源的Python框架，旨在帮助生物声学与机器学习领域的研究人员实现并利用基于深度学习的算法进行声学音频分析。Soundbay提供了一个直观易用的平台，可轻松将现有模型应用于自定义数据，或便捷地创建新模型。该框架的主要优势之一是能够在不同基准测试中比较基线模型，这对于当前深度学习算法在动物叫声分析领域的新兴研究与发展至关重要。我们通过在多数据集上建立鲸豚类叫声检测基准，展示了这一能力。该框架通过https://github.com/deep-voice/soundbay 公开发布。