georgid
I bring technology closer to the society by creating innovative, AI-enabled, software solutions - mainly in the domains of music, speech and natural language
Music Technology GroupBarcelona
Pinned Repositories
AlignmentDuration
Lyrics-to-audio-alignement system. Based on Machine Learning Algorithms: Hidden Markov Models with Viterbi forced alignment. The alignment is explicitly aware of durations of musical notes. The phonetic model are classified with MLP Deep Neural Network.
AlignmentEvaluation
Scripts for computing common lyrics-to-audio alignment evaluation metrics. Usable evaluation for any token-based alignment (e.g. if token is word, phrase, note, section etc.) User for the evaluation of the MIREX Lyrics-to-audio challenge
chorus-vocal-covers
A heuristic approach to the detection of choruses in vocal cover versions. Done at the WiMIR workshop at ISMIR 2019 https://docs.google.com/presentation/d/1WYXxChgo8DI_NknyndPdcOuxlhAL_428Olg2fWaVy6U/edit#slide=id.g6f4f88d309_0_57
ENST-drums-dataset
the dataset used in the paper https://drive.google.com/file/d/0B4bIMgQlCAuqdGVRbVNNbzJfeUU/view
HMMDuration
Python Hidden Markov Models framework. Adapted for computationally optimal Viterbi forced alignment. Added Explicit Duration model
htkModelParser
Parses models created by the HTK Toolkit (http://htk.eng.cam.ac.uk/) as text files into Python class. It enables then various operations with the models like visualization and comparison.
lakh_vocal_segments_dataset
singing voice with annotations of vocal onsets, based on the matched MIDI from http://colinraffel.com/projects/lmd/
Lyrics2AudioAligner
lyrics-to-audio-alignement system. Initially done using HTK for rapid prototyping
pypYIN
python pYIN
vocal-detection
georgid's Repositories
georgid/AlignmentDuration
Lyrics-to-audio-alignement system. Based on Machine Learning Algorithms: Hidden Markov Models with Viterbi forced alignment. The alignment is explicitly aware of durations of musical notes. The phonetic model are classified with MLP Deep Neural Network.
georgid/AlignmentEvaluation
Scripts for computing common lyrics-to-audio alignment evaluation metrics. Usable evaluation for any token-based alignment (e.g. if token is word, phrase, note, section etc.) User for the evaluation of the MIREX Lyrics-to-audio challenge
georgid/lakh_vocal_segments_dataset
singing voice with annotations of vocal onsets, based on the matched MIDI from http://colinraffel.com/projects/lmd/
georgid/Lyrics2AudioAligner
lyrics-to-audio-alignement system. Initially done using HTK for rapid prototyping
georgid/pypYIN
python pYIN
georgid/chorus-vocal-covers
A heuristic approach to the detection of choruses in vocal cover versions. Done at the WiMIR workshop at ISMIR 2019 https://docs.google.com/presentation/d/1WYXxChgo8DI_NknyndPdcOuxlhAL_428Olg2fWaVy6U/edit#slide=id.g6f4f88d309_0_57
georgid/otmm_vocal_segments_dataset
Manual annotations of audio segments that correspond to sections from score with singing voice present
georgid/SourceFilterContoursMelody
Melody extraction based on source-filter modelling
georgid/music_hack_sofia
Examples of extracting acoustic features with essentia
georgid/meowify
georgid/mfcc-htk-an-librosa
Reproduce the htk-type of MFCC features using the essentia framework. The MFCC extracted with essentia are compared to these extracted with htk these extracted with librosa
georgid/PhDThesis
The data needed to generate my phd thesis
georgid/Position-DBN-HMM-Lyrics
query by textual lyrics in audio with HHMM model of section positions using Viterbi
georgid/tune_puzzle
Tune Puzzle
georgid/align-magix
making a few web apps for testing
georgid/Curation_Users
georgid/docker
My Docker scripts and Dockerfile for several frameworks.
georgid/dunya
The Dunya music browser. Developed using Django 2
georgid/englishMLP2turkish
scripts to create mapping from English phoneme models as feed forward network multilayer perceptron network onto a GMM turksih phoneme model
georgid/essentia
C++ library of algorithms to extract features from audio files, including Python bindings.
georgid/IMFCC-visualization
Example of the inverse MFCC essentia feature
georgid/madmom
Python audio and music signal processing library. This is a fork adding support for synchronous tracking of vocal note onsets and metrical position in bar. The model used is Dynamic Bayesian Networks.
georgid/makam_acapella
acapella recordings of Makam
georgid/msaf
Music Structure Analysis Framework
georgid/pdnn
PDNN: A Python Toolkit for Deep Learning. http://www.cs.cmu.edu/~ymiao/pdnntk.html
georgid/publications_PhD
latex/lyx code and figures to reproduce the papers of my research http://mtg.upf.edu/biblio/author/810 that are the basis for my PhD http://compmusic.upf.edu/phd-thesis-georgi
georgid/searchByLyricsEval
evaluation scripts for search by lyrics (a.k.a. keyphrase spotting)
georgid/SINGmasterAndrioidWithGUI
sing master exrecise mode with complete GUI
georgid/turkish_makam_section_dataset
The section test dataset for classical Ottoman-Turkish makam music
georgid/your_first_neural_network