arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.12693cs.SDeess.AS
收藏

识别声音事件分类的操作

Identifying Actions for Sound Event Classification

Microsoft(微软);Bosch Research(博世研究院)

Benjamin Elizalde, Radu Revutchi, Samarjit Das, Bhiksha Raj, Ian Lane, Laurie M. Heller

摘要:

在心理学中,动作对于人类识别声音事件至关重要。在机器学习(ML)中,动作识别实现了高准确性;然而,还没有人问识别动作是否有利于声音事件分类(SEC),而不是将音频直接映射到声音事件。因此,我们提出了一种新的心理学启发的方法,包括通过人类听众的行动识别SEC。为了实现这一目标,我们使用众包让听众识别20个动作,这些动作单独或组合可能产生了精心研究的数据集ESC-50中的50个声音事件中的任何一个。每个音频记录的结果注释第一次将动作与声音事件的数据库相关联。注释用于创建称为动作向量(AV)的语义表示。我们通过比较AV与两种类型的音频特征-对数梅尔频谱图和最先进的音频嵌入来评估SEC。由于音频特征和AV捕获声学内容的不同抽象,我们将它们结合起来,并实现了最高的准确率(88%)。

英文摘要:

In Psychology, actions are paramount for humans to identify sound events. In Machine Learning (ML), action recognition achieves high accuracy; however, it has not been asked whether identifying actions can benefit Sound Event Classification (SEC), as opposed to mapping the audio directly to a sound event. Therefore, we propose a new Psychology-inspired approach for SEC that includes identification of actions via human listeners. To achieve this goal, we used crowdsourcing to have listeners identify 20 actions that in isolation or in combination may have produced any of the 50 sound events in the well-studied dataset ESC-50. The resulting annotations for each audio recording relate actions to a database of sound events for the first time. The annotations were used to create semantic representations called Action Vectors (AVs). We evaluated SEC by comparing the AVs with two types of audio features -- log-mel spectrograms and state-of-the-art audio embeddings. Because audio features and AVs capture different abstractions of the acoustic content, we combined them and achieved one of the highest reported accuracies (88%).

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。

↑