five

Dataset for Close Miking Empirical Practice Verification: A Source Separation Approach

收藏
NIAID Data Ecosystem2026-03-11 收录
下载链接:
https://zenodo.org/records/580778
下载链接
链接失效反馈
官方服务:
资源简介:
A dataset consisting of audio files which serve as support material to the following work: "Close Miking Empirical Practice Verification: A Source Separation Approach" by K. Drossos, S.I. Mimilakis, A. Floros, T. Virtanen and G. Schuller. The audio files contain information about two kind of signals a noise (pink noise) and a guitar (musical source) signal. For each signal multiple recordings, using a sampling frequency of 44.1kHz@16-bit, exist which are dependent upon the following variables:     - Mircophone type (polar pattern: Omni-directional and cardioid lobe)   @Corresponding Folders: Omni & Card     - Microphone angle (30 and 45 degrees only for the cardioid microphone) @Corresponding Folders: C30 & C45     - Sound pressure levels for the source (SPLs) and the noise(SPLn) (SPLs : 94dB, 97dB, 100dB || SPLn: 88dB, 91dB, 94dB, 97dB, 100dB)     - 12 Distances in meters: 0.03m - 0.30m with a step size of 0.03m & 0.30m - 1.00m with a step size of 0.35m Each recording set contains also the original "clean" sources and their mixture for all the above configurations.      The equipment used to record the above signals:     -Sound level meter (SLM): B&K 2250 Type A SLM      -Mic. A: & Shure SM57, dynamic, cardioid     -Mic. B: & Behringer ECM8000, condenser, omni-directional     -Laptop: Macbook Pro 15''     -Recording software: Digidesign ProTools M-Powered 8     -Musical instrument amplifier:  Behringer V-Tone GMX212     -Digital sound card: M-Audio Fast Track Ultra     -Loudspeaker: Electrovoice SX300      All recordings took place on the main stage of an empty municipal theater in Lixoyri, Kefallonia, Greece. The authors would like to thank the Department of Technology of Sound and Musical Instruments, Technological Educational Institute of Ionian Islands, for providing the equipment for the measurements.
创建时间:
2020-01-24
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作