Discover @georgid Open Source projects

Georgi Dzhambazov (@georgid)

georgid

Stars
157
Global Rank 148,587 (Top 6 %)
Followers 58
Following 3
Registered about 11 years ago
Most used languages

Python
55.6 %

Jupyter Notebook
16.7 %

MATLAB
11.1 %

Swift
5.6 %

Shell
5.6 %

TeX
5.6 %
Location 🇪🇸 Spain
Country Total Rank 1,780
Country Ranking

MATLAB
231

Jupyter Notebook
273

Python
369

TeX
428

Swift
598

Shell
833

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

lakh_vocal_segments_dataset

singing voice with annotations of vocal onsets, based on the matched MIDI from http://colinraffel.com/projects/lmd/

Jupyter Notebook

Lyrics2AudioAligner

lyrics-to-audio-alignement system. Initially done using HTK for rapid prototyping

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.

ENST-drums-dataset

the dataset used in the paper https://drive.google.com/file/d/0B4bIMgQlCAuqdGVRbVNNbzJfeUU/view

vocal-detection

otmm_vocal_segments_dataset

Manual annotations of audio segments that correspond to sections from score with singing voice present

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

music_hack_sofia

Examples of extracting acoustic features with essentia

Jupyter Notebook

redisCover

A tool to rediscover your favorite song: its cover versions. You just name the song, it does all for you: find all cover versions of the original, select their audio thumbnails, play a thumbnail mashup

JingjuAlignment

Lyrics-to-Audio Alignment for Jingju Arias

turkish-makam-lyrics-2-audio-test-data

Audio Files and symbTr description and word-level ground truth annotation of lyrics. Used to evaluate lyrics-to-audio alignement system

meowify

turkish-makam-lyrics-2-audio-test-data-synthesis

same as release of turkish-makam-lyrics-2-audio-test-data, but instead of original audio, the resynthesized versions.

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

Jupyter Notebook

PhDThesis

The data needed to generate my phd thesis

tune_puzzle

lyrics2AudioDTW

matlab version of lyrics2audio using DTW. experimental

Position-DBN-HMM-Lyrics

query by textual lyrics in audio with HHMM model of section positions using Viterbi