arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.02422cs.SDcs.LGeess.AS
收藏

使用主动学习高效标注生物声学声音事件的聚合策略

Aggregation Strategies for Efficient Annotation of Bioacoustic Sound Events Using Active Learning

RISE Research Institutes of Sweden(瑞典RISE研究院);Climate AI Nordics(北欧气候人工智能中心)

Richard Lindholm, Oscar Marklund, Olof Mogren, John Martinsson

AI总结:

提出一种名为 Top K Entropy 的主动学习不确定性聚合策略,通过优先选择最不确定的音频片段进行标注,仅需 8% 标签即可达到全量数据训练性能,显著提升了生物声学监测场景中的标注效率。

摘要:

声音事件检测(SED)应用中收集的大量音频数据需要高效的标注策略以实现监督学习。人工标注昂贵且耗时,使得主动学习(AL)成为减少标注工作量的有效方法。我们提出了 Top K Entropy,一种用于 AL 的新型不确定性聚合策略,它优先选择音频录音中最不确定的片段,而非对所有片段的不确定性取平均值。该方法能够选择整段录音进行标注,提高了稀疏数据场景下的效率。我们将 Top K Entropy 与随机采样和 Mean Entropy 进行了比较,结果表明更少的标签即可达到相同的模型性能,特别是在声音事件稀疏的数据集中。评估在包含狐獴、狗和婴儿哭声事件的公园录音混合音频上进行,代表了真实的生物声学监测场景。使用 Top K Entropy 进行主动学习,仅需 8% 的标签即可获得与在全标注数据集上训练相当的性能。Top K Entropy 优于 Mean Entropy,表明最好让最不确定的片段代表整个音频文件的不确定性。研究结果突显了 AL 在音频和时间序列应用(包括生物声学)中实现可扩展标注的潜力。

英文摘要:

The vast amounts of audio data collected in Sound Event Detection (SED) applications require efficient annotation strategies to enable supervised learning. Manual labeling is expensive and time-consuming, making Active Learning (AL) a promising approach for reducing annotation effort. We introduce Top K Entropy, a novel uncertainty aggregation strategy for AL that prioritizes the most uncertain segments within an audio recording, instead of averaging uncertainty across all segments. This approach enables the selection of entire recordings for annotation, improving efficiency in sparse data scenarios. We compare Top K Entropy to random sampling and Mean Entropy, and show that fewer labels can lead to the same model performance, particularly in datasets with sparse sound events. Evaluations are conducted on audio mixtures of sound recordings from parks with meerkat, dog, and baby crying sound events, representing real-world bioacoustic monitoring scenarios. Using Top K Entropy for active learning, we can achieve comparable performance to training on the fully labeled dataset with only 8% of the labels. Top K Entropy outperforms Mean Entropy, suggesting that it is best to let the most uncertain segments represent the uncertainty of an audio file. The findings highlight the potential of AL for scalable annotation in audio and time-series applications, including bioacoustics.

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。

↑