Name: Carlos Lordelo
Type: User
Company: Epidemic Sound
Bio: I am an engineer/computer scientist passionate about music. Most of my projects here are signal processing/machine learning methods applied to this topic.
Twitter: cpvlordelo
Location: Stockholm, Sweden
Blog: cpvlordelo.github.io
Carlos Lordelo's Projects
Code accompanying the paper "Semi-supervised adversarial audio source separation applied to singing voice extraction"
Carlos' personal webpage
DOOM-style 3D (raycasting) Game in Python Pygame
Genre Classification performed on GTZAN dataset.
Machine Learning Operations (MLOps) workshop
Sample code and notebooks for Generative AI on Google Cloud
Pretty basic theme for Hugo that covers all of the essentials. All you have to do is start typing!
Code for the ISMIR 2021 tutorial "Programming MIR Baselines from Scratch: Three Cases Studies"
Build Lambda deployment packages faster with Docker
Music Structure Analysis Framework
Automatic music transcription using semantic segmentation model. Reached state-of-the-art score on MAPS and MusicNet.
Instructional notebooks on music information retrieval.
This repo contains the automatic musictrack removal algorithm I implemented for my master's degree thesis.
Open-Unmix - Music Source Separation for PyTorch
ISMIR2018 Tutorial on Open Source and Reproducibility in MIR Research
Personal Website developed in Hugo based on hello-friend-ng theme
Repository with the code I implemented for my Bachelor Degree Project. It is my own implementation of the following paper: Z. Duan, Y. Zhang, C. Zhang and Z. Shi, "Unsupervised Single-Channel Music Source Separation by Average Harmonic Structure Modeling," in *IEEE Transactions on Audio, Speech, and Language Processing*, vol. 16, no. 4, May 2008
A lightweight yet powerful audio-to-MIDI converter with pitch bend detection
ISMIR 2021 Tutorial on Tempo, Beat and Downbeat estimation