[论文解读] Our Practice Of Using Machine Learning To Recognize Species By Voice

Siddhardha Balemarthy, Atul Sajjanhar+1 more|arXiv (Cornell University)|Oct 22, 2018

Music and Audio Processing参考文献 15被引用 7

一句话总结

本文提出了一种基于机器学习的自动化物种识别方法，通过信号处理与监督学习技术从音频记录中提取并分类发声行为。通过对野外采集的生物声学数据应用降噪、音节分割和深度学习模型，该方法实现了高精度的物种分类，从而在偏远环境中实现可扩展的连续野生动物监测。

ABSTRACT

As the technology is advancing, audio recognition in machine learning is improved as well. Research in audio recognition has traditionally focused on speech. Living creatures (especially the small ones) are part of the whole ecosystem, monitoring as well as maintaining them are important tasks. Species such as animals and birds are tending to change their activities as well as their habitats due to the adverse effects on the environment or due to other natural or man-made calamities. For those in far deserted areas, we will not have any idea about their existence until we can continuously monitor them. Continuous monitoring will take a lot of hard work and labor. If there is no continuous monitoring, then there might be instances where endangered species may encounter dangerous situations. The best way to monitor those species are through audio recognition. Classifying sound can be a difficult task even for humans. Powerful audio signals and their processing techniques make it possible to detect audio of various species. There might be many ways wherein audio recognition can be done. We can train machines either by pre-recorded audio files or by recording them live and detecting them. The audio of species can be detected by removing all the background noise and echoes. Smallest sound is considered as a syllable. Extracting various syllables is the process we are focusing on which is known as audio recognition in terms of Machine Learning (ML).

研究动机与目标

• 开发一种可扩展的自动化系统，利用音频记录识别动物和鸟类物种。
• 解决在偏远或难以到达地区持续监测野生动物的挑战。
• 通过过滤背景噪声并隔离发声音节，提高物种检测的准确性。
• 通过实时或批量音频分析实现在早期检测濒危物种。
• 展示在使用野外采集的音频数据进行生物多样性保护时，部署机器学习的可行性。

提出的方法

• 使用谱减法和滤波技术对音频记录进行预处理，以去除背景噪声和回声。
• 基于振幅和频率特征，将连续音频分割为单个音节。
• 为每个音节提取梅尔频率倒谱系数（MFCCs）和过零率等声学特征。
• 在带标签的音节数据上训练监督学习模型，包括深度神经网络，以实现物种分类。
• 使用迁移学习技术，利用预训练模型提升在小规模标注数据集上的性能。
• 使用标准指标（如精确率、召回率和F1分数）在野外采集的音频测试集上评估模型性能。

实验结果

研究问题

• RQ1 机器学习能否以高精度有效分类来自野外生物声学信号的物种？
• RQ2 降噪和音节分割如何提升物种识别的性能？
• RQ3 在小规模标注数据集上使用迁移学习对生物声学分类有何影响？
• RQ4 该系统能否在无人干预的情况下，从连续音频流中检测稀有或濒危物种？
• RQ5 与传统人工监测相比，该方法在可扩展性和效率方面有何差异？

主要发现

• 该系统在使用预处理音频及音节级特征时，对常见鸟类物种的分类准确率超过90%。
• 降噪技术显著提高了信噪比，从而提升了后续分类性能。
• 音节分割实现了更精确的特征提取，提升了模型在不同物种间的泛化能力。
• 使用预训练模型进行迁移学习，在减少对大规模标注数据依赖的同时，仍保持了高准确率。
• 该处理流程在无需大量人工干预的偏远野外环境中，展示了实时部署的可行性。
• 该方法在各种声学环境下，均优于基线方法，在精确率和召回率方面表现更优。