Georgi Dzhambazov's repositories
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.
ENST-drums-dataset
the dataset used in the paper https://drive.google.com/file/d/0B4bIMgQlCAuqdGVRbVNNbzJfeUU/view
JingjuAlignment
Lyrics-to-Audio Alignment for Jingju Arias
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
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
lyrics2AudioDTW
matlab version of lyrics2audio using DTW. experimental
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.
DrumTranscriptionWithBarPointer
matlab prototype for drum transcription sytem described in the paper https://drive.google.com/file/d/0B4bIMgQlCAuqdGVRbVNNbzJfeUU/view
intervalTrainer
smart-phone game app that teaches a technique to memorise music intervals. check out demo video:
musicBrainzTools
Tools to match MB to other datasets/collections (like echonest)
scikit-learn
scikit-learn: machine learning in Python
SINGmasterAndroid
First prototype with GUI for android
utilsLyrics
utilsLyrics
Varnam_lyricsannotation
Annotation with lyrics of varnams sections. Two level annotation: 1) lyrics for whole varnam recording as .lyricstxt file 2) file-level lyrics annoation for each lyrics section: .TextGrid