GUITAR-FX-DIST: A Dataset of Processed Guitar Recordings for Music Research - (Poly Continuous)

GUITAR-FX-DIST is a dataset of electric guitar recordings processed with overdrive, distortion and fuzz audio effects. It was developed for research in guitar effects detection, classification and parameters estimation. The dataset is also useful for research on automatic music transcription, intelligent music production, signal processing or effects modelling. It contains both unprocessed and processed recordings. The dataset is split into 4 sub-datasets: Mono Continuous, Mono Discrete, Poly Continuous, Poly Discrete Authors: Marco Comunità - Centre for Digital Music, Queen Mary University of London Reference: If you make use of GUITAR-FX-DIST, please cite the following publication: @article{comunità2021guitar,
title={Guitar Effects Recognition and Parameter Estimation with Convolutional Neural Networks},
author={Comunità, Marco and Stowell, Dan and Reiss, Joshua D.},
journal={Journal of the Audio Engineering Society},
year={2021},
volume={69},
number={7/8},
pages={594-604},
doi={},
month={July}
} Dataset Snapshot: Size: ~550k samples (~305 hours) + 550k mel spectrograms Audio Format: WAV - 44.1kHz, 16bit, mono, -6dBFS Mel-Spectrogram Format: NPY - 128 frequency bands, sample rate 22050Hz, window length 1024, hop size 512, Effects: 14 between overdrive, distortion and fuzz Unprocessed recordings 624 monophonic notes 420 polyphonic (2, 3 and 4 notes intervals and chords) 2 guitars, with up to 2 pick-up settings and up to 3 plucking styles (finger pluck - hard, finger pluck - soft, pick) Schecter Diamond C-1 Classic Chester Stratocaster Samples length: 2 sec Unprocessed Recordings: The original (unprocessed) recordings are from the IDMT-SMT-Audio-Effects dataset. For details please refer to the website and the accompagning publication: Stein, Michael; Abeßer, Jakob; Dittmar, Christian; Schuller, Gerald: Automatic Detection of Audio Effects in Guitar and Bass Recordings. Proceedings of the AES 128th Convention, 2010. Processed Recordings: The processed recordings are divided into 4 sub-datasets which are named depending on the unprocessed recordings used (monophonic or polyphonic) and on the settings' values (discrete or continuous). The sub-datasets are called: Mono Discrete, Poly Discrete, Mono Continuous, Poly Continuous Mono Discrete and Poly Discrete use a discrete set of combinations selected as the most common and representative settings a person might use (see README file for details). For Mono Continuous and Poly Continuous both unprocessed samples as well as settings’ values are drawn from a uniform distribution (10000 samples for each effect). Samples: Mono Discrete: ~160k Poly Discrete: ~110k Mono Continuous: 140k Poly Continuous: 140k Scripts: The dataset includes the MATLAB scripts used to generate the samples

GUITAR-FX-DIST是一款针对经过过载（overdrive）、失真（distortion）与法兹（fuzz）音频效果处理的电吉他录音数据集。该数据集专为吉他效果检测、分类与参数估计领域的研究开发，同时也可应用于自动音乐记谱、智能音乐制作、信号处理乃至效果建模相关研究。数据集包含原始未处理与经过效果处理的两类录音，并被划分为4个子集：单音连续（Mono Continuous）、单音离散（Mono Discrete）、复音连续（Poly Continuous）与复音离散（Poly Discrete）。

作者：马可·科穆尼蒂（Marco Comunità）——伦敦大学玛丽女王学院数字音乐中心

引用说明：若使用GUITAR-FX-DIST数据集，请引用如下文献：
@article{comunità2021guitar,
title={Guitar Effects Recognition and Parameter Estimation with Convolutional Neural Networks},
author={Comunità, Marco and Stowell, Dan and Reiss, Joshua D.},
journal={Journal of the Audio Engineering Society},
year={2021},
volume={69},
number={7/8},
pages={594-604},
doi={},
month={July}
}

数据集概览：
样本规模：约55万条样本（总计约305小时），附带55万条梅尔频谱图（mel-spectrogram）
音频格式：WAV格式，采样率44.1kHz，位深度16bit，单声道，峰值电平-6dBFS
梅尔频谱图格式：NPY格式，包含128个频带，采样率22050Hz，窗长1024，步长512
效果类型：涵盖过载、失真、法兹三类效果，共14种组合

原始未处理录音：包含624条单音（monophonic）音符录音与420条复音（polyphonic）（2、3、4音符音程与和弦）录音。所用吉他为Schecter Diamond C-1 Classic与Chester Stratocaster两款，每款吉他支持最多2种拾音器配置与3种拨奏方式：手指硬拨、手指软拨、拨片拨奏。单条样本时长为2秒。

原始未处理录音说明：原始（未处理）录音源自IDMT-SMT-Audio-Effects数据集。如需了解详情，请参考其官方网站及配套文献：Stein, Michael; Abeßer, Jakob; Dittmar, Christian; Schuller, Gerald: Automatic Detection of Audio Effects in Guitar and Bass Recordings. Proceedings of the AES 128th Convention, 2010.

效果处理录音说明：经过效果处理的录音被划分为4个子集，命名规则基于所用原始录音类型（单音或复音）以及效果参数设置类型（离散或连续），具体子集名称为：单音离散、复音离散、单音连续与复音连续。其中，单音离散与复音离散子集采用经筛选的离散参数组合集，这些组合为日常使用中最常见且具代表性的效果设置（详细说明请参阅README文件）；单音连续与复音连续子集的原始样本及效果参数值均取自均匀分布，每种效果对应10000条样本。

各子集样本规模：
单音离散子集：约16万条
复音离散子集：约11万条
单音连续子集：14万条
复音连续子集：14万条

配套脚本：数据集包含用于生成样本的MATLAB脚本

搜集汇总

背景与挑战

背景概述

GUITAR-FX-DIST是一个包含电吉他处理录音的数据集，主要用于音乐效果研究和信号处理。其Poly Continuous子集包含14万个样本，采用均匀分布生成样本和效果参数，适用于多种音乐研究应用。