There is a newer version of the record available.

Published August 24, 2016 | Version v0.9.0
Software Open

tomato: tomato v0.9.0

Creators

  • 1. Universitat Pompeu Fabra
  • 2. Dcode Soft

Description

tomato

Turkish-Ottoman Makam (M)usic Analysis TOolbox

Introduction

tomato is a comprehensive and easy-to-use toolbox for the analysis of audio recordings and music scores of Turkish-Ottoman makam music. The toolbox includes the state of art methodologies applied on this music tradition. The analysis tasks include:

  • Audio Analysis: audio metadata crawling, predominant melody extraction, tonic and transposition identification, makam recognition, histogram analysis, tuning analysis, melodic progression analysis
  • Symbolic Analysis: score metadata extraction, score section extraction, score phrase segmentation, semiotic section and phrase analysis
  • Joint Analysis: score-informed tonic identification and tempo estimation, section linking, note-level audio-score alignment, predominant melody octave correction, note models, (usul tracking is coming soon)

The aim of the toolbox is to allow the user to easily analyze large-scale audio recording and music score collections of Turkish-Ottoman makam music, using the state of the art methodologies specifically designed for the culture-specific characteristics of this tradition. The analysis results can then be further used for several tasks such as automatic content description, music discovery/recommendation and musicological analysis.

For the methodologies and their implementations in the toolbox, please refer to the References.

Changelog
  • Integrated makam recognition
  • Added training models precomputed from otmm_makam_recognition_dataset for tonic identification and makam recognition
  • Fizes a bug where method parameters setters of pitch distribution and makam recognizer (stored in tow dictionaries) are failed to be set
  • Incremented the version of morty in requirements
Tomato in a Nutshell
# import ... from tomato.joint.completeanalyzer import CompleteAnalyzer from matplotlib import pyplot as plt # score input symbtr_name = 'makam--form--usul--name--composer' txt_score_filename = 'path/to/txt_score' mu2_score_filename = 'path/to/mu2_score' # audio input audio_filename = 'path/to/audio' audio_mbid = '9244b2e0-6327-4ae3-9e8d-c0da54d39140' # MusicBrainz Identifier # instantiate analyzer object completeAnalyzer = CompleteAnalyzer() # Apply the complete analysis. The resulting tuple will have # (summarized_features, score_features, audio_features, # score_informed_audio_features, joint_features) in order results = completeAnalyzer.analyze( symbtr_name=symbtr_name, symbtr_txt_filename=txt_score_filepath, symbtr_mu2_filename=mu2_score_filepath, audio_filename=audio_filepath, audio_metadata=audio_mbid) # plot the summarized features fig, ax = completeAnalyzer.plot(results[0]) ax[0].set_ylim([50, 500]) plt.show()

You can refer to the jupyter notebooks in demos folder for detailed, interactive examples.

Installation

There are four steps in the installation:

  1. Installing tomato
  2. Installing Essentia
  3. Installing MATLAB Runtime
  4. Installing LilyPond (optional)
Installing tomato

The requirements of tomato require several packages to be installed. In Linux, you have to install the python 2.7, libxml2, libxslt1, freetype and png development packages packages. The package names might vary in different Linux distributions. In Ubuntu 16.04, you can install these packages by:

sudo apt-get install python-dev libxml2-dev libxslt1-dev libfreetype6-dev libpng12-dev

It is recommended to install tomato and its dependencies into a virtualenv. In the terminal, do the following:

virtualenv env source env/bin/activate

Then change the current directory to the repository folder and install by:

cd path/to/tomato python setup.py install

The requirements are installed during the setup. If that step does not work for some reason, you can install the requirements by calling:

pip install -r requirements

If you want to edit files in the package and want the changes reflected, you should call:

cd path/to/tomato pip install -e .

To run the demos, you need to install Jupyter Notebook:

pip install jupyter Installing Essentia

tomato uses several modules in Essentia. Follow the instructions to install the library. Then you should link the python bindings of Essentia in the virtual environment:

ln -s path_to_essentia_bindings path_to_env/lib/python2.7/site-packages

Don't forget to change the path_to_essentia_bindings and path_to_env with the actual path of the installed Essentia Python bindings and the path of your virtualenv, respectively. Depending on the Essentia version, the default installation path of the Essentia bindings is either /usr/local/lib/python2.7/dist-packages/essentia or /usr/local/lib/python2.7/site-packages/essentia.

Installing MATLAB Runtime

The score phrase segmentation, score-informed joint tonic identification and tempo estimation, section linking and note-level audio-score alignment algorithms are implemented in MATLAB and compiled as binaries. They need MATLAB Runtime for R2015a (8.5) to run. You should download and install this specific version (links for Linux and Mac OSX).

We recommend you to install MATLAB Runtime in the default installation path, as tomato searches them automatically. Otherwise, you have to specify your own path in the MATLAB Runtime configuration file, tomato/config/mcr_path.cfg.

Installing LilyPond

If you want to convert the music scores to svg format, LilyPond is a good choice, because it adds a mapping between each musical element in the LilyPond file and in the related svg.

To install LilyPond in Mac OSX, simply go to the Download page in the LilyPond website and follow the instructions for your operating system.

In most Linux distributions, you can install LilyPond from the software repository of your distribution. However, the version might be outdated. If the version is below 2.18.2, we recommend you to download the latest stable version from the LilyPond website. If you had to install LilyPond this way, you should enter the LilyPond binary path to the "custom" field in tomato/config/lilypond.cfg (the default location is $HOME/bin/lilypond).

Documentation

Coming soon...

License

The source code hosted in this repository is licenced under Affero GPL version 3. Any data (the audio recordings, music scores, extracted features, training models, figures, outputs etc.) are licenced under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

FAQ

  1. The notes aligned by JointAnalyzer.align_audio_score(...) seems shifted. What is the problem?

    Your audio input is probably a compressed format such as mp3. There are typically shifts between different decoders (and even different versions of the same decoder), when they decode the same compressed audio file. In the predominant melody extraction step (AudioAnalyzer.extract_pitch(...)), Essentia has to decode the recording for processing. You observe a shift, when the application you use another decoder.

    These shifts are typically small (e.g. 50 samples ~1ms), so they are not very problematic. Nevertheless, there is no guarantee that the shift will be bigger. If you need "perfect" synchronization, you should use an uncompressed format such as wav as the audio input.

    Note: In demos, we use mp3, because it would be too bulky to host a wav file.

  2. Which operating systems are suppported?

    The algorithms, which are written purely in Python, are platform independent. However compiling Essentia in Windows is not straightforward yet. Therefore we have only compiled the MATLAB binaries for Mac OSX and Linux. If you have compiled Essentia for Windows somehow or if you have any OS specific problems, please let us know by submitting an issue.

  3. What are the supported Python versions?

    Even though the code in the tomato package is compilant with both Python 3+ and Python 2.7, most of the requirements runs only in Python 2.7. We will start working on Python 3+ support, as soon as the Essentia bindings for Python 3 are available.

  4. Where are the MATLAB binaries?

    The binaries are not stored in tomato, because they relatively big. It would take too much space to store them here, including the versions introduced in each modification. Instead the binaries are provided within the releases of the relevant packages. The binaries are downloaded to tomato/bin during the installation process of tomato. Please refer to tomato/config/bin.cfg for the relevant releases.

  5. ScoreConverter says that "The lilypond path is not found". How can I fix the error?

    There can be similar problems regarding this issue:

    • The user-provided filepath (the music score input) does not exist.

      Check your input MusicXML-score path.

    • LilyPond is not installed.

      Install the latest stable verions for your OS.

    • The binary path exists but it is not used.

      The path is not searched by the defaults defined in tomato/config/lilypond.cfg. Add the path of the LilyPond binary to the configuration file.

Authors

Sertan Şentürk contact@sertansenturk.com

Acknowledgements

We would like to thank Harold Hagopian, the founder of Traditional Crossroads, for allowing us to use Tanburi Cemil Bey's performance of Uşşak Sazsemaisi in our demos.

References

Thesis

Files

tomato-v0.9.0.zip

Files (6.7 MB)

Name Size Download all
md5:24774dbb49e3490b5a269c752c73d0ab
6.7 MB Preview Download

Additional details

Related works

Is supplement to
https://github.com/sertansenturk/tomato/tree/v0.9.0 (URL)