arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.07640cs.SDcs.LGeess.ASstat.AP
收藏

大规模音频录音中发声的检测与分类

Detection and classification of vocal productions in large scale audio recordings

Aix Marseille Univ(艾克斯-马赛大学);CNRS(法国国家科学研究中心);Résurgences R&D(Résurgences研发公司)

Guillem Bonafos, Pierre Pudlo, Jean-Marc Freyermuth, Thierry Legou, Joël Fagot, Samuel Tronçon, Arnaud Rey

AI总结:

本文提出一种基于深度神经网络的端到端自动流水线,通过迁移学习、数据增强和贝叶斯优化等技术,在少量标注数据下实现大规模自然音频中发声的检测与分类,并在狒狒和婴儿录音上验证了高准确率和大规模处理能力。

摘要:

我们提出了一种自动数据处理流水线,用于从大规模自然音频录音中提取发声并对其进行分类。该流水线基于深度神经网络,同时解决这两个问题。通过一系列计算步骤(加窗、噪声类创建、数据增强、重采样、迁移学习、贝叶斯优化),它能够自动训练神经网络,而无需大量标注数据样本和大量计算资源。我们的端到端方法可以处理在不同录音条件下录制的含噪录音。我们在两个不同的自然音频数据集上对其进行了测试,一个来自灵长类研究中心录制的一组几内亚狒狒,另一个来自在家中录制的人类婴儿。该流水线在72分钟和77分钟的标注音频录音上训练模型,准确率分别为94.58%和99.76%。随后,它被用于处理443小时和174小时的自然连续录音,并分别创建了两个新的数据库,时长分别为38.8小时和35.2小时。我们讨论了这种方法的优势和局限性,该方法可应用于任何大规模音频录音。

英文摘要:

We propose an automatic data processing pipeline to extract vocal productions from large-scale natural audio recordings and classify these vocal productions. The pipeline is based on a deep neural network and adresses both issues simultaneously. Though a series of computationel steps (windowing, creation of a noise class, data augmentation, re-sampling, transfer learning, Bayesian optimisation), it automatically trains a neural network without requiring a large sample of labeled data and important computing resources. Our end-to-end methodology can handle noisy recordings made under different recording conditions. We test it on two different natural audio data sets, one from a group of Guinea baboons recorded from a primate research center and one from human babies recorded at home. The pipeline trains a model on 72 and 77 minutes of labeled audio recordings, with an accuracy of 94.58% and 99.76%. It is then used to process 443 and 174 hours of natural continuous recordings and it creates two new databases of 38.8 and 35.2 hours, respectively. We discuss the strengths and limitations of this approach that can be applied to any massive audio recording.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑