Vehicle Interior Sound Dataset

The used dataset is collected from the point of view (PoV) driving of different vehicle types from YouTube ("https://www.youtube.com/," 2020). These are only vehicle interior sounds. There is no driver or any human voice.5980 sounds were recorded with 8 classes. These vehicles were driven on asphalt roads in open-air. We didn’t prefer to collect interior vehicle sounds on unpaved roads in rainy weather. The file format of these data is wav. The length of the used sounds is in the range of 3-5 seconds with 48 kHz frequency. The chosen vehicle types are bus, minibus, pickup, sports car, jeep, truck, crossover, and car (automobile). The attributes of the collected vehicle interior sound (VIS) dataset are summarized in Table. No Class name Number of Samples No Class name Number of Samples 1 Bus 850 5 Jeep 600 2 Minibus 600 6 Truck 900 3 Pickup 680 7 Crossover 800 4 Sports Car 800 8 Car (C Class – 4K) 750 Total 5980 This dataset was used in the article given below. Researchers who want to use the DataSet should cite the specified article. Akbal, E., Tuncer, T., & Dogan, S. (2022). Vehicle Interior Sound Classification Based on Local Quintet Magnitude Pattern and Iterative Neighborhood Component Analysis. Applied Artificial Intelligence, 36(1), 2137653.

本数据集采集自YouTube平台（https://www.youtube.com/，2020）中不同车型的第一视角（Point of View, PoV）驾驶场景，仅包含车辆内部音频，无驾驶员或其他人类语音。本次共收录5980条音频样本，涵盖8个类别。所有测试车辆均在露天沥青路面行驶，未采集非铺装路面或雨天环境下的车辆内部音频。
本次收录的音频文件格式为wav，采样率为48 kHz，单段音频时长介于3至5秒之间。选取的车型包括巴士、小型巴士、皮卡、跑车、吉普车、卡车、跨界车以及乘用车（轿车）。
本采集的车辆内部音频（Vehicle Interior Sound, VIS）数据集的各项样本属性汇总如下：
1. 巴士：850条
2. 小型巴士：600条
3. 皮卡：680条
4. 跑车：800条
5. 吉普车：600条
6. 卡车：900条
7. 跨界车：800条
8. 乘用车（C级轿车，4K规格）：750条
总计：5980条

本数据集已应用于下述研究论文。如需使用该数据集的研究者，请引用以下文献：
Akbal, E., Tuncer, T., & Dogan, S. (2022). 基于局部五重幅值模式与迭代邻域成分分析的车辆内部音频分类. 应用人工智能, 36(1), 2137653.

搜集汇总

背景与挑战

背景概述

该数据集是一个车辆内部声音数据集，包含5980个WAV格式的音频样本，分为8种车辆类型（如巴士、小巴、皮卡等），每个音频长度为3-5秒，采样频率为48 kHz。数据来源于YouTube上的驾驶视角视频，仅包含车辆内部声音，无人声，适用于声音分类研究。