arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.00962eess.AScs.LGcs.SD
收藏

You Only Hear Once:一种类YOLO的音频分割和声音事件检测算法

You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection

University of Plymouth(普利茅斯大学);Plymouth Marine Laboratory(普利茅斯海洋实验室)

Satvik Venkatesh, David Moffat, Eduardo Reck Miranda

摘要:

音频分割和声音事件检测是机器听力中的关键主题,旨在检测声学类别及其各自的边界。它对音频内容分析、语音识别、音频索引和音乐信息检索都很有用。近年来,大多数研究文章采用逐类分段的方法。该技术将音频划分为小帧,并单独对这些帧执行分类。在本文中,我们提出了一种名为You Only Hear Once(YOHO)的新方法,该方法受到计算机视觉中普遍采用的YOLO算法的启发。我们将声学边界的检测转换为回归问题,而不是基于帧的分类。这是通过使用单独的输出神经元来检测音频类的存在并预测其开始和结束点来完成的。与最先进的卷积递归神经网络相比,YOHO的F度量的相对改进在音频分割和声音事件检测的多个数据集上的范围从1%到6%。由于YOHO的输出是端到端的,并且需要预测的神经元更少,因此推理速度至少比分段分类快6倍。此外,由于这种方法直接预测声学边界,因此后处理和平滑速度约为7倍。

英文摘要:

Audio segmentation and sound event detection are crucial topics in machine listening that aim to detect acoustic classes and their respective boundaries. It is useful for audio-content analysis, speech recognition, audio-indexing, and music information retrieval. In recent years, most research articles adopt segmentation-by-classification. This technique divides audio into small frames and individually performs classification on these frames. In this paper, we present a novel approach called You Only Hear Once (YOHO), which is inspired by the YOLO algorithm popularly adopted in Computer Vision. We convert the detection of acoustic boundaries into a regression problem instead of frame-based classification. This is done by having separate output neurons to detect the presence of an audio class and predict its start and end points. The relative improvement for F-measure of YOHO, compared to the state-of-the-art Convolutional Recurrent Neural Network, ranged from 1% to 6% across multiple datasets for audio segmentation and sound event detection. As the output of YOHO is more end-to-end and has fewer neurons to predict, the speed of inference is at least 6 times faster than segmentation-by-classification. In addition, as this approach predicts acoustic boundaries directly, the post-processing and smoothing is about 7 times faster.

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。

↑