/audio_ml

This Project is a MonoRepo which contains all the Audio `Exploratory Data Analysis (E.D.A)` and Machine Learning Models along with cited DataSets. This project will also hold Distributed Partitioned Streamable DataSets generated and stored in Cloud Object Storage after experiments

Primary LanguageJupyter Notebook

Audio/Music Information Retrieval and Machine Learning

This Project is a MonoRepo which contains all the Audio Exploratory Data Analysis (E.D.A) and Machine Learning Models along with cited DataSets.

This project will also hold Distributed Partitioned Streamable DataSets generated by after experiments

NOTE: Models and Training snapshots,algorithms are kept private. Use the methods described in correcponding sections to stream the data sets from kaggleor multiple cloud storages

DataSets

https://www.kaggle.com/datasets/arpanpathak/original-and-cover-song-pairs

About Dataset

This dataset contains 80 pairs of song and their cover. These RAW wav files ares sourced from ISMIR webscrapping. https://www.ismir.net/resources/datasets/

Each of the songs in the pair is organized in a directory same as the name of the song title.

Download and extract the archive and read the README.md for covers80 package

This is a set of data and code to support the MIREX cover song identification task.

The directory covers32k/ contains 80 songs with two versions of each, all encoded as 32 kbps MP3 (mono, 16k sampling, bandwidth limited to 7 kHz). The basis of this set was cover versions .

REFERENCES

@InProceedings{ brian_mcfee-proc-scipy-2015,
  author    = { {B}rian {M}c{F}ee and {C}olin {R}affel and {D}awen {L}iang and {D}aniel {P}.{W}. {E}llis and {M}att {M}c{V}icar and {E}ric {B}attenberg and {O}riol {N}ieto },
  title     = { librosa: {A}udio and {M}usic {S}ignal {A}nalysis in {P}ython },
  booktitle = { {P}roceedings of the 14th {P}ython in {S}cience {C}onference },
  pages     = { 18 - 24 },
  year      = { 2015 },
  editor    = { {K}athryn {H}uff and {J}ames {B}ergstra },
  doi       = { 10.25080/Majora-7b98e3ed-003 }
}