A small project where I identify notes and key harmonies in a piece of music and use them further to recreate and generate the same piece of music through Python

Related tags

AudioMusic
Overview

Music-notes-detection

This project has 3 parts to it:

  1. Note-detection which can detect a note in a song
  2. Scale detection which can detect the scale a song is based on
  3. Generating music notes from the frequencies, further leading to making songs

Note detection:

Here I have used the fast Fourier transformation method to convert time frames to frequency frames. The musical note frequency is found at the first peak of frequency-amplitude plot (the graph resultant from the Fast Fourier Transform).

The Fourier transform is a sophisticated signal analysis technique that is utilised in a variety of applications, including audio processing and picture compression. In its scipy.fft module, SciPy offers a comprehensive implementation.

Note: this program can only be used for detecting a single note that is most dominant from a given wav file. The corresponding frequency of the note will have the largest peak in the Fast Fourier Transform, after which it can be mapped to the exact note.

The plots are explained below for the violin solo of the song Canon in D taken from here

This image is for the density of the notes in the song (raw data)

soundplot

This image is after performing the Fast Fourier Transform on the normalisation applied to the raw song

FFT

Scale Detection:

For idenitfying the scale of the song, I have used the music21 toolkit, available for python. This module has several functions to detect the principal key signature of a song and identifies the scale using the Krumhansl-Schmuckler algorithm. I have expanded on how the algorithm is used in the writeup on the page linked here.

The Krumhansl-Schmuckler algorithm was developed, and it was built on the concept that the pitch class distribution of the notes in a piece of music could reveal its tonality essentially by computing the similarity of the distribution with each of the 12 major and minor profiles, and predicting the most associated key.

Generating Music

Now we can generate and recreate music. After getting all the notes from a particular song (for this use music_notes_detection.py at an extremely slow framerate such that it can identify each and every single note), we can put them all together while specifying a particular note length for each note.

After generating one note, I have plotted the results and can be explained below:

This image is for the sound wave of the note generated

soundplot

This image is after performing the Fast Fourier Transform on the note generated, notice the singular peak at the corresponding frequency

FFT

There are a few parameters we keep in mind like the bar length (specified by the time-signature of a song - most commonly it is 4/4, for waltz it is 3/4 and so on - it can be thought as the number of crotchets in particular time frame), the ADSR levels (Attack, Decay, Sustain and Release) that are used to control the loudness of the song and the sustain levels, which are concerned with how long a note needs to be sustained with for how long.

In this piece of code I have recreated the first part of the violin duet of Canon in D. Any song can be recreated in this way, as long as the length of the bar specified is not violated and the notes are known.

The command to Run Code:

For note and key detection,

$ python3 music_notes_detection.py

For generating the scale (the first part of generation):

$ python3 music_notes_generator.py

For generating the song (the second part of generation):

$ python3 song.py
convert-to-opus-cli is a Python CLI program for converting audio files to opus audio format.

convert-to-opus-cli convert-to-opus-cli is a Python CLI program for converting audio files to opus audio format. Installation Must have installed ffmp

4 Dec 21, 2022
Pyrogram bot to automate streaming music in voice chats

Pyrogram bot to automate streaming music in voice chats Help If you face an error, want to discuss this project or get support for it, join it's group

Roj 124 Oct 21, 2022
AudioDVP:Photorealistic Audio-driven Video Portraits

AudioDVP This is the official implementation of Photorealistic Audio-driven Video Portraits. Major Requirements Ubuntu = 18.04 PyTorch = 1.2 GCC =

232 Jan 03, 2023
This is an OverPowered Vc Music Player! Will work for you and play music in Voice Chatz

VcPlayer This is an OverPowered Vc Music Player! Will work for you and play music in Voice Chatz Telegram Voice-Chat Bot [PyTGCalls] ⇝ Requirements ⇜

1 Dec 20, 2021
A Python wrapper around the Soundcloud API

soundcloud-python A friendly wrapper around the Soundcloud API. Installation To install soundcloud-python, simply: pip install soundcloud Or if you'r

SoundCloud 84 Dec 31, 2022
This is a realtime voice translator program which gets input from user at any language and converts it to the desired language that the user asks

This is a realtime voice translator program which gets input from user at any language and converts it to the desired language that the user asks ...

Mohan Ram S 1 Dec 30, 2021
A collection of free MIDI chords and progressions ready to be used in your DAW, Akai MPC, or Roland MC-707/101

A collection of free MIDI chords and progressions ready to be used in your DAW, Akai MPC, or Roland MC-707/101

921 Jan 05, 2023
Real-Time Spherical Microphone Renderer for binaural reproduction in Python

ReTiSAR Implementation of the Real-Time Spherical Microphone Renderer for binaural reproduction in Python [1][2]. Contents: | Requirements | Setup | Q

Division of Applied Acoustics at Chalmers University of Technology 51 Dec 17, 2022
Tradutor de um arquivo MIDI para ser usado em um simulador RISC-V(RARS)

Tradutor_MIDI-RISC-V Tradutor de um arquivo MIDI para ser usado em um simulador RISC-V(RARS) *O resultado sai com essa formatação: nota,duração,nota,d

Gabriel B. G. 4 Sep 02, 2022
MelGAN test on audio decoding

Official repository for the paper MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis The original work URL: https://github.com

Jurio 1 Apr 29, 2022
Scalable audio processing framework written in Python with a RESTful API

TimeSide : scalable audio processing framework and server written in Python TimeSide is a python framework enabling low and high level audio analysis,

Parisson 340 Jan 04, 2023
TwitterMusicBot - A Twitter bot with Spotify integration.

A Twitter Music Bot 🤖 🎵 🎶 I created this project to learn more about APIs, so it only works for student purposes. Initially, delving into the Spoti

Gustavo Oliveira 2 Jan 02, 2022
An audio digital processing toolbox based on a workflow/pipeline principle

AudioTK Audio ToolKit is a set of audio filters. It helps assembling workflows for specific audio processing workloads. The audio workflow is split in

Matthieu Brucher 238 Oct 18, 2022
Synthesia but open source, made in python and free

PyPiano Synthesia but open source, made in python and free Requirements are in requirements.txt If you struggle with installation of pyaudio, run : pi

DaCapo 11 Nov 06, 2022
python script for getting mp3 files from yaoutube playlist

mp3-from-youtube-playlist python script for getting mp3 files from youtube playlist. Do your non-tech brown relatives ask you for downloading music fr

Shuhan Mirza 7 Oct 19, 2022
[Singing Log] Let your program learn to sing!

[Singing Log] Let your program learn to sing! You must have thought this was changelog when you saw the English title, but it's not, it's chànggēlog. What it does is allow your program to print logs

黄巍 22 Sep 03, 2022
Open-Source bot to play songs in your Telegram's Group Voice Chat. Powered by @Akki_ThePro

VcPlayer Telegram Voice-Chat Bot [PyTGCalls] ⇝ Requirements ⇜ Account requirements A Telegram account to use as the music bot, You cannot use regular

Akki ThePro 2 Dec 25, 2021
A Python port and library-fication of the midicsv tool by John Walker.

A Python port and library-fication of the midicsv tool by John Walker. If you need to convert MIDI files to human-readable text files and back, this is the library for you.

Tim Wedde 52 Dec 29, 2022
❤️ Hi There Im Cozmo Music Bot A next gen powerful telegram group Music bot for get your Songs and music @Venuja_Sadew

🎵 Cozmo MUSIC 🎵 Cozmo Music is a Music powerfull bot for playing music on telegram voice chat groups. Requirements FFmpeg NodeJS nodesource.com Pyth

Venuja Sadew 3 Jan 08, 2022
a library for audio and music analysis

aubio aubio is a library to label music and sounds. It listens to audio signals and attempts to detect events. For instance, when a drum is hit, at wh

aubio 2.9k Dec 30, 2022