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