Metadata-Version: 2.1
Name: asmd
Version: 0.5.1
Summary: Audio-Score Meta-Dataset
Home-page: https://asmd.readthedocs.org
License: MIT
Author: Federico Simonetta
Author-email: federico.simonetta@unimi.it
Requires-Python: >=3.8.5,<4.0.0
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Other Audience
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Topic :: Multimedia :: Sound/Audio
Requires-Dist: alive-progress (>=1.3.3,<2.0.0)
Requires-Dist: beautifulsoup4 (>=4.8.2,<5.0.0)
Requires-Dist: decorator (>=4.4.1,<5.0.0)
Requires-Dist: essentia (>=2.1b6.dev374,<3.0)
Requires-Dist: hmmlearn (>=0.2.5,<0.3.0)
Requires-Dist: joblib (>=0.14.1,<0.15.0)
Requires-Dist: mega.py (>=1.0.6,<2.0.0)
Requires-Dist: numpy (>=1.18.1,<2.0.0)
Requires-Dist: plotly (>=4.4.1,<5.0.0)
Requires-Dist: pretty_midi (>=0.2.8,<0.3.0)
Requires-Dist: prompt_toolkit (>=3.0.3,<4.0.0)
Requires-Dist: pyfiglet (>=0.8.post1,<0.9)
Requires-Dist: requests (>=2.22.0,<3.0.0)
Requires-Dist: scikit_learn (>=0.22.1,<0.23.0)
Requires-Dist: setuptools (>=45.2.0,<46.0.0)
Requires-Dist: tqdm (>=4.43.0,<5.0.0)
Project-URL: Documentation, https://asmd.readthedocs.org
Project-URL: Repository, https://gitlab.di.unimi.it/federicosimonetta/asmd/
Description-Content-Type: text/x-rst

Audio-Score Meta-Dataset
========================

ASMD is a framework for installing, using and creating music multimodal
datasets including (for now) audio and scores.

This is the repository for paper [1] 

Read more in the docs_.

* To install: ``pip install asmd``
* To install datasets: ``python -m asmd.install``
* To import API: ``from asmd import asmd``

Other examples in the paper!

.. _docs: https://asmd.readthedocs.org

Changelog
=========

Version 0.5
^^^^^^^^^^^

#. Improved inference of misalignments
#. Improved the reproducibility of artificial data
#. Improved the documentation
#. Added `ASAP` group in **Maestro: broken backward compatibility**
#. Added `score` for the original score
#. Added midi note matching based on EITA method
#. Added missing and extra notes
#. General refactoring
#. Added functions for set operations among datasets (union, intersections,
   complement and subsampling)
#. Various fixes

Version 0.4
^^^^^^^^^^^
# Skipped

Version 0.3
^^^^^^^^^^^

#. Fixed MIDI values ([0, 128) for control changes and pitches)
#. Fixed metadata error while reading audio files
#. Fixed pedaling for tracks that have no pedaling
#. Fixed group selection
#. Added `get_songs`
#. Improved initialization of `Dataset` objects
#. Improved documentation

Version 0.2.2-2
^^^^^^^^^^^^^^^

#. Fixed major bug in install script
#. Fixed bug in conversion tool
#. Removed TRIOS dataset because no longer available
#. Updated ground_truth

Version 0.2.2
^^^^^^^^^^^^^

#. Improved ``parallel`` function
#. Improved documentation
#. Various fixings in ``get_pedaling``

Version 0.2.1
^^^^^^^^^^^^^

#. Added ``nframes`` utility to compute the number of frames in a given time lapse
#. Added ``group`` attribute to each track to create splits in a dataset
   (supported in only Maestro for now)
#. Changed ``.pyx`` to ``.py`` with cython in pure-python mode

Version 0.2
^^^^^^^^^^^

#. Added ``parallel`` utility to run code in parallel over a while dataset
#. Added ``get_pianoroll`` utility to get score as pianoroll
#. Added ``sustain``, ``sostenuto``, and ``soft`` to model pedaling information
#. Added utilities ``frame2time`` and ``time2frame`` to ease the development
#. Added ``get_audio_data`` to get data about audio without loading it
#. Added ``get_score_duration`` to get the full duration of a score without
   loading it
#. Added another name for the API: ``from asmd import asmd``
#. Deprecated ``from asmd import audioscoredataset``
#. Changed the ``generate_ground_truth`` command line options
#. Easier to generate misaligned data
#. Improved documentation

Roadmap
=======

#. Add matching of same music piece among different datasets
#. Added `torch.DatasetDump` for preprocessing datasets and use them in pytorch
#. Add new modalities (video, images)
#. Add other datasets
#. Refactoring of the `filter` function (it's a bit long now...)

Cite us
=======

[1]  Simonetta, Federico ; Ntalampiras, Stavros ; Avanzini, Federico: *ASMD: an automatic framework for compiling multimodal datasets with audio and scores*. In: Proceedings of the 17th Sound and Music Computing Conference. Torino, 2020 arXiv:2003.01958_

.. _arXiv:2003.01958: https://arxiv.org/abs/2003.01958

---

Federico Simonetta 

#. https://federicosimonetta.eu.org
#. https://lim.di.unimi.it

