update
This commit is contained in:
553
html/pythonscientificaudio.md2.html
Normal file
553
html/pythonscientificaudio.md2.html
Normal file
@@ -0,0 +1,553 @@
|
||||
<h1 id="python-for-scientific-audio">Python for Scientific Audio</h1>
|
||||
<p><a href="https://github.com/sindresorhus/awesome"><img
|
||||
src="https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg"
|
||||
alt="Awesome" /></a> <a
|
||||
href="https://github.com/faroit/awesome-python-scientific-audio/actions?query=workflow%3ACI+branch%3Amaster+event%3Apush"><img
|
||||
src="https://github.com/faroit/awesome-python-scientific-audio/workflows/CI/badge.svg"
|
||||
alt="Build Status" /></a></p>
|
||||
<p>The aim of this repository is to create a comprehensive, curated list
|
||||
of python software/tools related and used for scientific research in
|
||||
audio/music applications.</p>
|
||||
<h2 id="contents">Contents</h2>
|
||||
<ul>
|
||||
<li><a href="#audio-related-packages">Audio Related Packages</a>
|
||||
<ul>
|
||||
<li><a href="#read-write">Read/Write</a></li>
|
||||
<li><a href="#transformations---general-dsp">Transformations - General
|
||||
DSP</a></li>
|
||||
<li><a href="#feature-extraction">Feature extraction</a></li>
|
||||
<li><a href="#data-augmentation">Data augmentation</a></li>
|
||||
<li><a href="#speech-processing">Speech Processing</a></li>
|
||||
<li><a href="#environmenta">Environmental Sounds</a></li>
|
||||
<li><a href="#perceptial-models---auditory-models">Perceptial Models -
|
||||
Auditory Models</a></li>
|
||||
<li><a href="#source-separation">Source Separation</a></li>
|
||||
<li><a href="#music-information-retrieval">Music Information
|
||||
Retrieval</a></li>
|
||||
<li><a href="#deep-learning">Deep Learning</a></li>
|
||||
<li><a href="#symbolic-music---midi---musicology">Symbolic Music - MIDI
|
||||
- Musicology</a></li>
|
||||
<li><a href="#realtime-applications">Realtime applications</a></li>
|
||||
<li><a href="#web-audio">Web - Audio</a></li>
|
||||
<li><a href="#audio-related-apis-and-datasets">Audio related APIs and
|
||||
Datasets</a></li>
|
||||
<li><a href="#wrappers-for-audio-plugins">Wrappers for Audio
|
||||
Plugins</a></li>
|
||||
</ul></li>
|
||||
<li><a href="#tutorials">Tutorials</a></li>
|
||||
<li><a href="#books">Books</a></li>
|
||||
<li><a href="#scientific-papers">Scientific Paper</a></li>
|
||||
<li><a href="#other-resources">Other Resources</a></li>
|
||||
<li><a href="#related-lists">Related lists</a></li>
|
||||
<li><a href="#contributing">Contributing</a></li>
|
||||
<li><a href="#license">License</a></li>
|
||||
</ul>
|
||||
<h2 id="audio-related-packages">Audio Related Packages</h2>
|
||||
<ul>
|
||||
<li>Total number of packages: 66</li>
|
||||
</ul>
|
||||
<h4 id="read-write">Read-Write</h4>
|
||||
<ul>
|
||||
<li><a href="https://github.com/danilobellini/audiolazy">audiolazy</a>
|
||||
<a href="https://github.com/danilobellini/audiolazy">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/audiolazy/">:package:</a> -
|
||||
Expressive Digital Signal Processing (DSP) package for Python.</li>
|
||||
<li><a href="https://github.com/beetbox/audioread">audioread</a> <a
|
||||
href="https://github.com/beetbox/audioread">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/audioread/">:package:</a> -
|
||||
Cross-library (GStreamer + Core Audio + MAD + FFmpeg) audio
|
||||
decoding.</li>
|
||||
<li><a href="https://mutagen.readthedocs.io/">mutagen</a> <a
|
||||
href="https://github.com/quodlibet/mutagen">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/mutagen">:package:</a> - Reads and
|
||||
writes all kind of audio metadata for various formats.</li>
|
||||
<li><a href="http://docs.mikeboers.com/pyav/">pyAV</a> <a
|
||||
href="https://github.com/mikeboers/PyAV">:octocat:</a> - PyAV is a
|
||||
Pythonic binding for FFmpeg or Libav.</li>
|
||||
<li><a href="http://pysoundfile.readthedocs.io/">(Py)Soundfile</a> <a
|
||||
href="https://github.com/bastibe/PySoundFile">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/SoundFile">:package:</a> - Library
|
||||
based on libsndfile, CFFI, and NumPy.</li>
|
||||
<li><a href="https://github.com/rabitt/pysox">pySox</a> <a
|
||||
href="https://github.com/rabitt/pysox">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/pysox/">:package:</a> - Wrapper for
|
||||
sox.</li>
|
||||
<li><a href="https://github.com/faroit/stempeg">stempeg</a> <a
|
||||
href="https://github.com/faroit/stempeg">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/stempeg/">:package:</a> - read/write
|
||||
of STEMS multistream audio.</li>
|
||||
<li><a href="https://github.com/devsnd/tinytag">tinytag</a> <a
|
||||
href="https://github.com/devsnd/tinytag">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/tinytag/">:package:</a> - reading
|
||||
music meta data of MP3, OGG, FLAC and Wave files.</li>
|
||||
</ul>
|
||||
<h4 id="transformations---general-dsp">Transformations - General
|
||||
DSP</h4>
|
||||
<ul>
|
||||
<li><a
|
||||
href="http://python-acoustics.github.io/python-acoustics/">acoustics</a>
|
||||
<a
|
||||
href="https://github.com/python-acoustics/python-acoustics/">:octocat:</a>
|
||||
<a href="https://pypi.python.org/pypi/acoustics">:package:</a> - useful
|
||||
tools for acousticians.</li>
|
||||
<li><a href="https://github.com/mbrucher/AudioTK">AudioTK</a> <a
|
||||
href="https://github.com/mbrucher/AudioTK">:octocat:</a> - DSP filter
|
||||
toolbox (lots of filters).</li>
|
||||
<li><a href="https://audiotsm.readthedocs.io/">AudioTSM</a> <a
|
||||
href="https://github.com/Muges/audiotsm">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/audiotsm/">:package:</a> - real-time
|
||||
audio time-scale modification procedures.</li>
|
||||
<li><a href="https://github.com/detly/gammatone">Gammatone</a> <a
|
||||
href="https://github.com/detly/gammatone">:octocat:</a> - Gammatone
|
||||
filterbank implementation.</li>
|
||||
<li><a href="http://pyfftw.github.io/pyFFTW/">pyFFTW</a> <a
|
||||
href="https://github.com/pyFFTW/pyFFTW">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/pyFFTW/">:package:</a> - Wrapper for
|
||||
FFTW(3).</li>
|
||||
<li><a href="https://grrrr.org/research/software/nsgt/">NSGT</a> <a
|
||||
href="https://github.com/grrrr/nsgt">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/nsgt">:package:</a> - Non-stationary
|
||||
gabor transform, constant-q.</li>
|
||||
<li><a href="https://github.com/sergree/matchering">matchering</a> <a
|
||||
href="https://github.com/sergree/matchering">:octocat:</a> <a
|
||||
href="https://pypi.org/project/matchering/">:package:</a> - Automated
|
||||
reference audio mastering.</li>
|
||||
<li><a href="https://github.com/nils-werner/mdct">MDCT</a> <a
|
||||
href="https://github.com/nils-werner/mdct">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/mdct">:package:</a> - MDCT
|
||||
transform.</li>
|
||||
<li><a href="http://pydub.com">pydub</a> <a
|
||||
href="https://github.com/jiaaro/pydub">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/mdct">:package:</a> - Manipulate
|
||||
audio with a simple and easy high level interface.</li>
|
||||
<li><a href="http://tftb.nongnu.org">pytftb</a> <a
|
||||
href="https://github.com/scikit-signal/pytftb">:octocat:</a> -
|
||||
Implementation of the MATLAB Time-Frequency Toolbox.</li>
|
||||
<li><a
|
||||
href="https://github.com/LCAV/pyroomacoustics">pyroomacoustics</a> <a
|
||||
href="https://github.com/LCAV/pyroomacoustics">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/pyroomacoustics">:package:</a> - Room
|
||||
Acoustics Simulation (RIR generator)</li>
|
||||
<li><a href="https://github.com/bmcfee/pyrubberband">PyRubberband</a> <a
|
||||
href="https://github.com/bmcfee/pyrubberband">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/pyrubberband/">:package:</a> -
|
||||
Wrapper for <a
|
||||
href="http://breakfastquay.com/rubberband/">rubberband</a> to do
|
||||
pitch-shifting and time-stretching.</li>
|
||||
<li><a href="http://pywavelets.readthedocs.io">PyWavelets</a> <a
|
||||
href="https://github.com/PyWavelets/pywt">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/PyWavelets">:package:</a> - Discrete
|
||||
Wavelet Transform in Python.</li>
|
||||
<li><a href="http://resampy.readthedocs.io">Resampy</a> <a
|
||||
href="https://github.com/bmcfee/resampy">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/resampy">:package:</a> - Sample rate
|
||||
conversion.</li>
|
||||
<li><a href="http://www.sfstoolbox.org">SFS-Python</a> <a
|
||||
href="https://github.com/sfstoolbox/sfs-python">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/sfs/">:package:</a> - Sound Field
|
||||
Synthesis Toolbox.</li>
|
||||
<li><a
|
||||
href="https://appliedacousticschalmers.github.io/sound_field_analysis-py/">sound_field_analysis</a>
|
||||
<a
|
||||
href="https://github.com/AppliedAcousticsChalmers/sound_field_analysis-py">:octocat:</a>
|
||||
<a href="https://pypi.org/project/sound-field-analysis/">:package:</a> -
|
||||
Analyze, visualize and process sound field data recorded by spherical
|
||||
microphone arrays.</li>
|
||||
<li><a href="http://stft.readthedocs.io">STFT</a> <a
|
||||
href="https://github.com/nils-werner/stft">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/stft">:package:</a> - Standalone
|
||||
package for Short-Time Fourier Transform.</li>
|
||||
</ul>
|
||||
<h4 id="feature-extraction">Feature extraction</h4>
|
||||
<ul>
|
||||
<li><a href="http://aubio.org/">aubio</a> <a
|
||||
href="https://github.com/aubio/aubio">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/aubio">:package:</a> - Feature
|
||||
extractor, written in C, Python interface.</li>
|
||||
<li><a href="https://github.com/libAudioFlux/audioFlux">audioFlux</a> <a
|
||||
href="https://github.com/libAudioFlux/audioFlux">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/audioflux">:package:</a> - A library
|
||||
for audio and music analysis, feature extraction.</li>
|
||||
<li><a href="https://github.com/danilobellini/audiolazy">audiolazy</a>
|
||||
<a href="https://github.com/danilobellini/audiolazy">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/audiolazy/">:package:</a> - Realtime
|
||||
Audio Processing lib, general purpose.</li>
|
||||
<li><a href="http://essentia.upf.edu">essentia</a> <a
|
||||
href="https://github.com/MTG/essentia">:octocat:</a> - Music related low
|
||||
level and high level feature extractor, C++ based, includes Python
|
||||
bindings.</li>
|
||||
<li><a
|
||||
href="https://github.com/jameslyons/python_speech_features">python_speech_features</a>
|
||||
<a
|
||||
href="https://github.com/jameslyons/python_speech_features">:octocat:</a>
|
||||
<a
|
||||
href="https://pypi.python.org/pypi/python_speech_features">:package:</a>
|
||||
- Common speech features for ASR.</li>
|
||||
<li><a href="https://github.com/Yaafe/Yaafe">pyYAAFE</a> <a
|
||||
href="https://github.com/Yaafe/Yaafe">:octocat:</a> - Python bindings
|
||||
for YAAFE feature extractor.</li>
|
||||
<li><a href="https://github.com/astorfi/speechpy">speechpy</a> <a
|
||||
href="https://github.com/astorfi/speechpy">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/speechpy">:package:</a> - Library for
|
||||
Speech Processing and Recognition, mostly feature extraction for
|
||||
now.</li>
|
||||
<li><a href="https://github.com/SuperKogito/spafe">spafe</a> <a
|
||||
href="https://github.com/SuperKogito/spafe">:octocat:</a> <a
|
||||
href="https://pypi.org/project/spafe/">:package:</a> - Python library
|
||||
for features extraction from audio files.</li>
|
||||
</ul>
|
||||
<h4 id="data-augmentation">Data augmentation</h4>
|
||||
<ul>
|
||||
<li><a
|
||||
href="https://github.com/iver56/audiomentations">audiomentations</a> <a
|
||||
href="https://github.com/iver56/audiomentations">:octocat:</a> <a
|
||||
href="https://pypi.org/project/audiomentations/">:package:</a> - Audio
|
||||
Data Augmentation.</li>
|
||||
<li><a href="https://muda.readthedocs.io/en/latest/">muda</a> <a
|
||||
href="https://github.com/bmcfee/muda">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/muda">:package:</a> - Musical Data
|
||||
Augmentation.</li>
|
||||
<li><a href="https://github.com/SuperKogito/pydiogment">pydiogment</a>
|
||||
<a href="https://github.com/SuperKogito/pydiogment">:octocat:</a> <a
|
||||
href="https://pypi.org/project/pydiogment/">:package:</a> - Audio Data
|
||||
Augmentation.</li>
|
||||
</ul>
|
||||
<h4 id="speech-processing">Speech Processing</h4>
|
||||
<ul>
|
||||
<li><a href="https://www.readbeyond.it/aeneas/">aeneas</a> <a
|
||||
href="https://github.com/readbeyond/aeneas/">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/aeneas/">:package:</a> - Forced
|
||||
aligner, based on MFCC+DTW, 35+ languages.</li>
|
||||
<li><a href="https://github.com/mozilla/DeepSpeech">deepspeech</a> <a
|
||||
href="https://github.com/mozilla/DeepSpeech">:octocat:</a> <a
|
||||
href="https://pypi.org/project/deepspeech/">:package:</a> - Pretrained
|
||||
automatic speech recognition.</li>
|
||||
<li><a href="https://github.com/lowerquality/gentle">gentle</a> <a
|
||||
href="https://github.com/lowerquality/gentle">:octocat:</a> -
|
||||
Forced-aligner built on Kaldi.</li>
|
||||
<li><a
|
||||
href="https://github.com/YannickJadoul/Parselmouth">Parselmouth</a> <a
|
||||
href="https://github.com/YannickJadoul/Parselmouth">:octocat:</a> <a
|
||||
href="https://pypi.org/project/praat-parselmouth/">:package:</a> -
|
||||
Python interface to the <a href="http://www.praat.org">Praat</a>
|
||||
phonetics and speech analysis, synthesis, and manipulation
|
||||
software.</li>
|
||||
<li><a
|
||||
href="https://persephone.readthedocs.io/en/latest/">persephone</a> <a
|
||||
href="https://github.com/persephone-tools/persephone">:octocat:</a> <a
|
||||
href="https://pypi.org/project/persephone/">:package:</a> - Automatic
|
||||
phoneme transcription tool.</li>
|
||||
<li><a
|
||||
href="https://github.com/pyannote/pyannote-audio">pyannote.audio</a> <a
|
||||
href="https://github.com/pyannote/pyannote-audio">:octocat:</a> <a
|
||||
href="https://pypi.org/project/pyannote-audio/">:package:</a> - Neural
|
||||
building blocks for speaker diarization.</li>
|
||||
<li><a
|
||||
href="https://github.com/tyiannak/pyAudioAnalysis">pyAudioAnalysis</a>²
|
||||
<a href="https://github.com/tyiannak/pyAudioAnalysis">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/pyAudioAnalysis/">:package:</a> -
|
||||
Feature Extraction, Classification, Diarization.</li>
|
||||
<li><a href="https://github.com/wiseman/py-webrtcvad">py-webrtcvad</a>
|
||||
<a href="https://github.com/wiseman/py-webrtcvad">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/webrtcvad/">:package:</a> - Interface
|
||||
to the WebRTC Voice Activity Detector.</li>
|
||||
<li><a href="https://github.com/vBaiCai/python-pesq">pypesq</a> <a
|
||||
href="https://github.com/vBaiCai/python-pesq">:octocat:</a> - Wrapper
|
||||
for the PESQ score calculation.</li>
|
||||
<li><a href="https://github.com/mpariente/pystoi">pystoi</a> <a
|
||||
href="https://github.com/mpariente/pystoi">:octocat:</a> <a
|
||||
href="https://pypi.org/project/pystoi">:package:</a> - Short Term
|
||||
Objective Intelligibility measure (STOI).</li>
|
||||
<li><a
|
||||
href="https://github.com/JeremyCCHsu/Python-Wrapper-for-World-Vocoder">PyWorldVocoder</a>
|
||||
<a
|
||||
href="https://github.com/JeremyCCHsu/Python-Wrapper-for-World-Vocoder">:octocat:</a>
|
||||
- Wrapper for Morise’s World Vocoder.</li>
|
||||
<li><a
|
||||
href="https://montrealcorpustools.github.io/Montreal-Forced-Aligner/">Montreal
|
||||
Forced Aligner</a> <a
|
||||
href="https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner">:octocat:</a>
|
||||
- Forced aligner, based on Kaldi (HMM), English (others can be
|
||||
trained).</li>
|
||||
<li><a href="http://lium.univ-lemans.fr/sidekit/">SIDEKIT</a> <a
|
||||
href="https://pypi.python.org/pypi/SIDEKIT/">:package:</a> - Speaker and
|
||||
Language recognition.</li>
|
||||
<li><a
|
||||
href="https://github.com/Uberi/speech_recognition">SpeechRecognition</a>
|
||||
<a href="https://github.com/Uberi/speech_recognition">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/SpeechRecognition/">:package:</a> -
|
||||
Wrapper for several ASR engines and APIs, online and offline.</li>
|
||||
</ul>
|
||||
<h4 id="environmental-sounds">Environmental Sounds</h4>
|
||||
<ul>
|
||||
<li><a href="http://tut-arg.github.io/sed_eval">sed_eval</a> <a
|
||||
href="https://github.com/TUT-ARG/sed_eval">:octocat:</a> <a
|
||||
href="https://pypi.org/project/sed_eval/">:package:</a> - Evaluation
|
||||
toolbox for Sound Event Detection</li>
|
||||
</ul>
|
||||
<h4 id="perceptial-models---auditory-models">Perceptial Models -
|
||||
Auditory Models</h4>
|
||||
<ul>
|
||||
<li><a href="https://github.com/mrkrd/cochlea">cochlea</a> <a
|
||||
href="https://github.com/mrkrd/cochlea">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/cochlea/">:package:</a> - Inner ear
|
||||
models.</li>
|
||||
<li><a href="http://briansimulator.org/">Brian2</a> <a
|
||||
href="https://github.com/brian-team/brian2">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/Brian2">:package:</a> - Spiking
|
||||
neural networks simulator, includes cochlea model.</li>
|
||||
<li><a href="https://github.com/deeuu/loudness">Loudness</a> <a
|
||||
href="https://github.com/deeuu/loudness">:octocat:</a> - Perceived
|
||||
loudness, includes Zwicker, Moore/Glasberg model.</li>
|
||||
<li><a
|
||||
href="https://www.christiansteinmetz.com/projects-blog/pyloudnorm">pyloudnorm</a>
|
||||
<a href="https://github.com/csteinmetz1/pyloudnorm">:octocat:</a> -
|
||||
Audio loudness meter and normalization, implements ITU-R BS.1770-4.</li>
|
||||
<li><a href="http://www.sfstoolbox.org">Sound Field Synthesis
|
||||
Toolbox</a> <a
|
||||
href="https://github.com/sfstoolbox/sfs-python">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/sfs/">:package:</a> - Sound Field
|
||||
Synthesis Toolbox.</li>
|
||||
</ul>
|
||||
<h4 id="source-separation">Source Separation</h4>
|
||||
<ul>
|
||||
<li><a href="https://github.com/aliutkus/commonfate">commonfate</a> <a
|
||||
href="https://github.com/aliutkus/commonfate">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/commonfate">:package:</a> - Common
|
||||
Fate Model and Transform.</li>
|
||||
<li><a href="https://github.com/stitchfix/NTFLib">NTFLib</a> <a
|
||||
href="https://github.com/stitchfix/NTFLib">:octocat:</a> - Sparse
|
||||
Beta-Divergence Tensor Factorization.</li>
|
||||
<li><a
|
||||
href="https://interactiveaudiolab.github.io/project/nussl.html">NUSSL</a>
|
||||
<a href="https://github.com/interactiveaudiolab/nussl">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/nussl">:package:</a> - Holistic
|
||||
source separation framework including DSP methods and deep learning
|
||||
methods.</li>
|
||||
<li><a href="http://nimfa.biolab.si">NIMFA</a> <a
|
||||
href="https://github.com/marinkaz/nimfa">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/nimfa">:package:</a> - Several
|
||||
flavors of non-negative-matrix factorization.</li>
|
||||
</ul>
|
||||
<h4 id="music-information-retrieval">Music Information Retrieval</h4>
|
||||
<ul>
|
||||
<li><a href="https://github.com/jvbalen/catchy">Catchy</a> <a
|
||||
href="https://github.com/jvbalen/catchy">:octocat:</a> - Corpus Analysis
|
||||
Tools for Computational Hook Discovery.</li>
|
||||
<li><a
|
||||
href="https://github.com/sevagh/chord-detection">chord-detection</a> <a
|
||||
href="https://github.com/sevagh/chord-detection">:octocat:</a> -
|
||||
Algorithms for chord detection and key estimation.</li>
|
||||
<li><a href="https://madmom.readthedocs.io/en/latest/">Madmom</a> <a
|
||||
href="https://github.com/CPJKU/madmom">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/madmom">:package:</a> - MIR packages
|
||||
with strong focus on beat detection, onset detection and chord
|
||||
recognition.</li>
|
||||
<li><a href="http://craffel.github.io/mir_eval/">mir_eval</a> <a
|
||||
href="https://github.com/craffel/mir_eval">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/mir_eval">:package:</a> - Common
|
||||
scores for various MIR tasks. Also includes bss_eval
|
||||
implementation.</li>
|
||||
<li><a href="http://pythonhosted.org/msaf/">msaf</a> <a
|
||||
href="https://github.com/urinieto/msaf">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/msaf">:package:</a> - Music Structure
|
||||
Analysis Framework.</li>
|
||||
<li><a href="http://librosa.github.io/librosa/">librosa</a> <a
|
||||
href="https://github.com/librosa/librosa">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/librosa">:package:</a> - General
|
||||
audio and music analysis.</li>
|
||||
</ul>
|
||||
<h4 id="deep-learning">Deep Learning</h4>
|
||||
<ul>
|
||||
<li><a href="https://github.com/keunwoochoi/kapre">Kapre</a> <a
|
||||
href="https://github.com/keunwoochoi/kapre">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/kapre">:package:</a> - Keras Audio
|
||||
Preprocessors</li>
|
||||
<li><a href="https://github.com/pytorch/audio">TorchAudio</a> <a
|
||||
href="https://github.com/pytorch/audio">:octocat:</a> - PyTorch Audio
|
||||
Loaders</li>
|
||||
<li><a href="https://github.com/KinWaiCheuk/nnAudio">nnAudio</a> <a
|
||||
href="https://github.com/KinWaiCheuk/nnAudio">:octocat:</a> <a
|
||||
href="https://pypi.org/project/nnAudio/">:package:</a> - Accelerated
|
||||
audio processing using 1D convolution networks in PyTorch.</li>
|
||||
</ul>
|
||||
<h4 id="symbolic-music---midi---musicology">Symbolic Music - MIDI -
|
||||
Musicology</h4>
|
||||
<ul>
|
||||
<li><a href="http://web.mit.edu/music21/">Music21</a> <a
|
||||
href="https://github.com/cuthbertLab/music21">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/music21">:package:</a> - Toolkit for
|
||||
Computer-Aided Musicology.</li>
|
||||
<li><a href="https://mido.readthedocs.io/en/latest/">Mido</a> <a
|
||||
href="https://github.com/olemb/mido">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/mido">:package:</a> - Realtime MIDI
|
||||
wrapper.</li>
|
||||
<li><a href="https://github.com/bspaans/python-mingus">mingus</a> <a
|
||||
href="https://github.com/bspaans/python-mingus">:octocat:</a> <a
|
||||
href="https://pypi.org/project/mingus">:package:</a> - Advanced music
|
||||
theory and notation package with MIDI file and playback support.</li>
|
||||
<li><a href="http://craffel.github.io/pretty-midi/">Pretty-MIDI</a> <a
|
||||
href="https://github.com/craffel/pretty-midi">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/pretty-midi">:package:</a> - Utility
|
||||
functions for handling MIDI data in a nice/intuitive way.</li>
|
||||
</ul>
|
||||
<h4 id="realtime-applications">Realtime applications</h4>
|
||||
<ul>
|
||||
<li><a href="https://github.com/nir/jupylet">Jupylet</a> <a
|
||||
href="https://github.com/nir/jupylet">:octocat:</a> - Subtractive,
|
||||
additive, FM, and sample-based sound synthesis.</li>
|
||||
<li><a href="http://ajaxsoundstudio.com/software/pyo/">PYO</a> <a
|
||||
href="https://github.com/belangeo/pyo">:octocat:</a> - Realtime audio
|
||||
dsp engine.</li>
|
||||
<li><a
|
||||
href="https://github.com/spatialaudio/python-sounddevice">python-sounddevice</a>
|
||||
<a href="http://python-sounddevice.readthedocs.io">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/sounddevice">:package:</a> -
|
||||
PortAudio wrapper providing realtime audio I/O with NumPy.</li>
|
||||
<li><a
|
||||
href="https://github.com/AppliedAcousticsChalmers/ReTiSAR">ReTiSAR</a>
|
||||
<a
|
||||
href="https://github.com/AppliedAcousticsChalmers/ReTiSAR">:octocat:</a>
|
||||
- Binarual rendering of streamed or IR-based high-order spherical
|
||||
microphone array signals.</li>
|
||||
</ul>
|
||||
<h4 id="web-audio">Web Audio</h4>
|
||||
<ul>
|
||||
<li><a href="https://github.com/Parisson/TimeSide/tree/dev">TimeSide
|
||||
(Beta)</a> <a
|
||||
href="https://github.com/Parisson/TimeSide/tree/dev">:octocat:</a> -
|
||||
high level audio analysis, imaging, transcoding, streaming and
|
||||
labelling.</li>
|
||||
</ul>
|
||||
<h4 id="audio-dataset-and-dataloaders">Audio Dataset and
|
||||
Dataloaders</h4>
|
||||
<ul>
|
||||
<li><p><a href="http://beets.io/">beets</a> <a
|
||||
href="https://github.com/beetbox/beets">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/beets">:package:</a> - Music library
|
||||
manager and <a href="https://musicbrainz.org/">MusicBrainz</a>
|
||||
tagger.</p></li>
|
||||
<li><p><a href="http://dsdtools.readthedocs.io">musdb</a> <a
|
||||
href="https://github.com/sigsep/sigsep-mus-db">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/musdb">:package:</a> - Parse and
|
||||
process the MUSDB18 dataset.</p></li>
|
||||
<li><p><a href="http://medleydb.readthedocs.io">medleydb</a> <a
|
||||
href="https://github.com/marl/medleydb">:octocat:</a> - Parse <a
|
||||
href="http://medleydb.weebly.com/">medleydb</a> audio +
|
||||
annotations.</p></li>
|
||||
<li><p><a
|
||||
href="https://github.com/soundcloud/soundcloud-python">Soundcloud
|
||||
API</a> <a
|
||||
href="https://github.com/soundcloud/soundcloud-python">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/soundcloud">:package:</a> - Wrapper
|
||||
for <a href="https://developers.soundcloud.com/">Soundcloud
|
||||
API</a>.</p></li>
|
||||
<li><p><a href="http://rg3.github.io/youtube-dl/">Youtube-Downloader</a>
|
||||
<a href="https://github.com/rg3/youtube-dl">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/youtube_dl">:package:</a> - Download
|
||||
youtube videos (and the audio).</p></li>
|
||||
<li><p><a href="https://github.com/ynop/audiomate">audiomate</a> <a
|
||||
href="https://github.com/ynop/audiomate">:octocat:</a> <a
|
||||
href="https://pypi.python.org/pypi/audiomate/">:package:</a> - Loading
|
||||
different types of audio datasets.</p></li>
|
||||
<li><p><a href="https://mirdata.readthedocs.io/en/latest/">mirdata</a>
|
||||
<a href="https://github.com/mir-dataset-loaders/mirdata">:octocat:</a>
|
||||
<a href="https://pypi.python.org/pypi/mirdata">:package:</a> - Common
|
||||
loaders for Music Information Retrieval (MIR) datasets. #### Wrappers
|
||||
for Audio Plugins</p></li>
|
||||
<li><p><a
|
||||
href="https://code.soundsoftware.ac.uk/projects/vampy-host">VamPy
|
||||
Host</a> <a href="https://pypi.python.org/pypi/vamp">:package:</a> -
|
||||
Interface compiled vamp plugins.</p></li>
|
||||
</ul>
|
||||
<h2 id="tutorials">Tutorials</h2>
|
||||
<ul>
|
||||
<li><a href="https://jakevdp.github.io/WhirlwindTourOfPython/">Whirlwind
|
||||
Tour Of Python</a> <a
|
||||
href="https://github.com/jakevdp/WhirlwindTourOfPython">:octocat:</a> -
|
||||
fast-paced introduction to Python essentials, aimed at researchers and
|
||||
developers.</li>
|
||||
<li><a href="http://www.scipy-lectures.org/index.html">Introduction to
|
||||
Numpy and Scipy</a> <a
|
||||
href="https://github.com/scipy-lectures/scipy-lecture-notes">:octocat:</a>
|
||||
- Highly recommended tutorial, covers large parts of the scientific
|
||||
Python ecosystem.</li>
|
||||
<li><a
|
||||
href="https://docs.scipy.org/doc/numpy/user/numpy-for-matlab-users.html">Numpy
|
||||
for MATLAB® Users</a> - Short overview of equivalent python functions
|
||||
for switchers.</li>
|
||||
<li><a href="http://musicinformationretrieval.com/">MIR Notebooks</a> <a
|
||||
href="https://github.com/stevetjoa/stanford-mir">:octocat:</a> -
|
||||
collection of instructional iPython Notebooks for music information
|
||||
retrieval (MIR).</li>
|
||||
<li><a
|
||||
href="https://github.com/spatialaudio/selected-topics-in-audio-signal-processing-exercises">Selected
|
||||
Topics in Audio Signal Processing</a> - Exercises as iPython
|
||||
notebooks.</li>
|
||||
<li><a href="https://www.youtube.com/watch?v=SSyQ0kRHzis">Live-coding a
|
||||
music synthesizer</a> Live-coding video showing how to use the
|
||||
SoundDevice library to reproduce realistic sounds. <a
|
||||
href="https://github.com/cool-RR/python_synthesizer">Code</a>.</li>
|
||||
</ul>
|
||||
<h2 id="books">Books</h2>
|
||||
<ul>
|
||||
<li><a
|
||||
href="https://github.com/jakevdp/PythonDataScienceHandbook">Python Data
|
||||
Science Handbook</a> - Jake Vanderplas, Excellent Book and accompanying
|
||||
tutorial notebooks.</li>
|
||||
<li><a
|
||||
href="https://www.audiolabs-erlangen.de/fau/professor/mueller/bookFMP">Fundamentals
|
||||
of Music Processing</a> - Meinard Müller, comes with Python
|
||||
exercises.</li>
|
||||
</ul>
|
||||
<h2 id="scientific-papers">Scientific Papers</h2>
|
||||
<ul>
|
||||
<li><a href="http://eprints.maynoothuniversity.ie/4115/1/40.pdf">Python
|
||||
for audio signal processing</a> - John C. Glover, Victor Lazzarini and
|
||||
Joseph Timoney, Linux Audio Conference 2011.</li>
|
||||
<li><a
|
||||
href="http://conference.scipy.org/proceedings/scipy2015/pdfs/brian_mcfee.pdf">librosa:
|
||||
Audio and Music Signal Analysis in Python</a>, <a
|
||||
href="https://www.youtube.com/watch?v=MhOdbtPhbLU">Video</a> - Brian
|
||||
McFee, Colin Raffel, Dawen Liang, Daniel P.W. Ellis, Matt McVicar, Eric
|
||||
Battenberg, Oriol Nieto, Scipy 2015.</li>
|
||||
<li><a href="https://arxiv.org/abs/1911.01255">pyannote.audio: neural
|
||||
building blocks for speaker diarization</a>, <a
|
||||
href="https://www.youtube.com/watch?v=37R_R82lfwA">Video</a> - Hervé
|
||||
Bredin, Ruiqing Yin, Juan Manuel Coria, Gregory Gelly, Pavel Korshunov,
|
||||
Marvin Lavechin, Diego Fustes, Hadrien Titeux, Wassim Bouaziz,
|
||||
Marie-Philippe Gill, ICASSP 2020.</li>
|
||||
</ul>
|
||||
<h2 id="other-resources">Other Resources</h2>
|
||||
<ul>
|
||||
<li><a
|
||||
href="https://www.coursera.org/learn/audio-signal-processing">Coursera
|
||||
Course</a> - Audio Signal Processing, Python based course from UPF of
|
||||
Barcelona and Stanford University.</li>
|
||||
<li><a
|
||||
href="http://dsp-nbsphinx.readthedocs.io/en/nbsphinx-experiment/index.html">Digital
|
||||
Signal Processing Course</a> - Masters Course Material (University of
|
||||
Rostock) with many Python examples.</li>
|
||||
<li><a href="https://mircommunity.slack.com">Slack Channel</a> - Music
|
||||
Information Retrieval Community.</li>
|
||||
</ul>
|
||||
<h2 id="related-lists">Related lists</h2>
|
||||
<p>There is already <a
|
||||
href="https://wiki.python.org/moin/PythonInMusic">PythonInMusic</a> but
|
||||
it is not up to date and includes too many packages of special interest
|
||||
that are mostly not relevant for scientific applications. <a
|
||||
href="https://github.com/vinta/awesome-python">Awesome-Python</a> is
|
||||
large curated list of python packages. However, the audio section is
|
||||
very small.</p>
|
||||
<h2 id="contributing">Contributing</h2>
|
||||
<p>Your contributions are always welcome! Please take a look at the <a
|
||||
href="CONTRIBUTING.md">contribution guidelines</a> first.</p>
|
||||
<p>I will keep some pull requests open if I’m not sure whether those
|
||||
libraries are awesome, you could vote for them by adding 👍 to them.</p>
|
||||
<h2 id="license">License</h2>
|
||||
<p><a href="https://creativecommons.org/licenses/by/4.0/"><img
|
||||
src="https://img.shields.io/badge/License-CC%20BY%204.0-lightgrey.svg"
|
||||
alt="License: CC BY 4.0" /></a></p>
|
||||
<p><a
|
||||
href="https://github.com/faroit/awesome-python-scientific-audio">pythonscientificaudio.md
|
||||
Github</a></p>
|
||||
Reference in New Issue
Block a user