2018:Audio Classification (Train/Test) Tasks

From MIREX Wiki

Audio Classification (Test/Train) tasks

Description

Many tasks in music classification can be characterized into a two-stage process: training classification models using labeled data and testing the models using new/unseen data. Therefore, we propose this "meta" task which includes various audio classification tasks that follow this Train/Test process. For MIREX 2018, six classification sub-tasks are included:

All six classification tasks were conducted in previous MIREX runs (please see MIREX 2017 Train-Test Task Results). This page presents the evaluation results of these tasks last year.


Task specific mailing list

In the past we have use a specific mailing list for the discussion of this task and related tasks. This year, however, we are asking that all discussions take place on the MIREX "EvalFest" list. If you have an question or comment, simply include the task name in the subject heading.

Data

Audio Classical Composer Identification

This dataset requires algorithms to classify music audio according to the composer of the track (drawn from a collection of performances of a variety of classical music genres). The collection used at MIREX 2009 will be re-used.

Collection statistics:

  • 2772 30-second 22.05 kHz mono wav clips
  • 11 "classical" composers (252 clips per composer), including:
    • Bach
    • Beethoven
    • Brahms
    • Chopin
    • Dvorak
    • Handel
    • Haydn
    • Mendelssohnn
    • Mozart
    • Schubert
    • Vivaldi

Audio US Pop Music Genre Classification

This dataset requires algorithms to classify music audio according to the genre of the track (drawn from a collection of US Pop music tracks). The MIREX 2007 Genre dataset will be re-used, which was drawn from the USPOP 2002 and USCRAP collections.

Collection statistics:

  • 7000 30-second audio clips in 22.05kHz mono WAV format
  • 10 genres (700 clips from each genre), including:
    • Blues
    • Jazz
    • Country/Western
    • Baroque
    • Classical
    • Romantic
    • Electronica
    • Hip-Hop
    • Rock
    • HardRock/Metal


Audio Latin Music Genre Classification

This dataset requires algorithms to classify music audio according to the genre of the track (drawn from a collection of Latin popular and dance music, sourced from Brazil and hand labeled by music experts). Carlos Silla's (cns2 (at) kent (dot) ac (dot) uk) Latin popular and dance music dataset [1] will be re-used. This collection is likely to contain a greater number of styles of music that will be differentiated by rhythmic characteristics than the MIREX 2007 dataset.

Collection statistics:

  • 3,227 audio files in 22.05kHz mono WAV format
  • 10 Latin music genres, including:
    • Axe
    • Bachata
    • Bolero
    • Forro
    • Gaucha
    • Merengue
    • Pagode
    • Sertaneja
    • Tango


Audio Mood Classification

This dataset requires algorithms to classify music audio according to the mood of the track (drawn from a collection of production msuic sourced from the APM collection [2]). The MIREX 2007 Mood Classification dataset [3] will be re-used.

Collection statistics:

  • 600 30 second audio clips in 22.05kHz mono WAV format selected from the APM collection [4], and labeled by human judges using the Evalutron6000 system.
  • 5 mood categories [5] each of which contains 120 clips:
    • Cluster_1: passionate, rousing, confident,boisterous, rowdy
    • Cluster_2: rollicking, cheerful, fun, sweet, amiable/good natured
    • Cluster_3: literate, poignant, wistful, bittersweet, autumnal, brooding
    • Cluster_4: humorous, silly, campy, quirky, whimsical, witty, wry
    • Cluster_5: aggressive, fiery,tense/anxious, intense, volatile,visceral

Audio Formats

For all datasets, participating algorithms will have to read audio in the following format:

  • Sample rate: 22 KHz
  • Sample size: 16 bit
  • Number of channels: 1 (mono)
  • Encoding: WAV


Evaluation

This section first describes evaluation methods common to all the datasets, then specifies settings unique to each of the tasks.

Participating algorithms will be evaluated with 3-fold cross validation. For Artist Identification and Classical Composer Classification, album filtering will be used the test and training splits, i.e. training and test sets will contain tracks from different albums; for US Pop Genre Classification and Latin Genre Classification, artist filtering will be used the test and training splits, i.e. training and test sets will contain different artists.

The raw classification (identification) accuracy, standard deviation and a confusion matrix for each algorithm will be computed.

Classification accuracies will be tested for statistically significant differences using Friedman's Anova with Tukey-Kramer honestly significant difference (HSD) tests for multiple comparisons. This test will be used to rank the algorithms and to group them into sets of equivalent performance.

In addition computation times for feature extraction and training/classification will be measured.


Submission Format

File I/O Format

The audio files to be used in these tasks will be specified in a simple ASCII list file. The formats for the list files are specified below:


Feature extraction list file

The list file passed for feature extraction will be a simple ASCII list file. This file will contain one path per line with no header line. I.e.

<example path and filename>

E.g.

/path/to/track1.wav
/path/to/track2.wav
...


Training list file

The list file passed for model training will be a simple ASCII list file. This file will contain one path per line, followed by a tab character and the class (artist, genre or mood) label, again with no header line.

I.e.

<example path and filename>\t<class label>

E.g.

/path/to/track1.wav	rock
/path/to/track2.wav	blues
...


Test (classification) list file

The list file passed for testing classification will be a simple ASCII list file identical in format to the Feature extraction list file. This file will contain one path per line with no header line.

I.e.

<example path and filename>

E.g.

/path/to/track1.wav
/path/to/track2.wav
...


Classification output file

Participating algorithms should produce a simple ASCII list file identical in format to the Training list file. This file will contain one path per line, followed by a tab character and the artist label, again with no header line.

I.e.

<example path and filename>\t<class label>

E.g.

/path/to/track1.wav	classical
/path/to/track2.wav	blues
...


Submission calling formats

Algorithms should divide their feature extraction and training/classification into separate runs. This will facilitate a single feature extraction step for the task, while training and classification can be run for each cross-validation fold.

Hence, participants should provide two executables or command line parameters for a single executable to run the two separate processes.

Executables will have to accept the paths to the aforementioned list files as command line parameters.

Scratch folders will be provided for all submissions for the storage of feature files and any model files to be produced. Executables will have to accept the path to their scratch folder as a command line parameter. Executables will also have to track which feature files correspond to which audio files internally. To facilitate this process, unique file names will be assigned to each audio track.


Example submission calling formats

 extractFeatures.sh /path/to/scratch/folder /path/to/featureExtractionListFile.txt
 TrainAndClassify.sh /path/to/scratch/folder /path/to/trainListFile.txt /path/to/testListFile.txt /path/to/outputListFile.txt
 extractFeatures.sh /path/to/scratch/folder /path/to/featureExtractionListFile.txt
 Train.sh /path/to/scratch/folder /path/to/trainListFile.txt 
 Classify.sh /path/to/scratch/folder /path/to/testListFile.txt /path/to/outputListFile.txt
 myAlgo.sh -extract /path/to/scratch/folder /path/to/featureExtractionListFile.txt
 myAlgo.sh -train /path/to/scratch/folder /path/to/trainListFile.txt 
 myAlgo.sh -classify /path/to/scratch/folder /path/to/testListFile.txt /path/to/outputListFile.txt

Multi-processor compute nodes will be used to run this task, however, we ask that submissions use no more than 4 cores (as we will be running a lot of submissions and will need to run some in parallel). Ideally, the number of threads to use should be specified as a command line parameter. Alternatively, implementations may be provided in hard-coded 1, 2 or 4 thread/core configurations.

 extractFeatures.sh -numThreads 4 /path/to/scratch/folder /path/to/featureExtractionListFile.txt
 TrainAndClassify.sh -numThreads 4 /path/to/scratch/folder /path/to/trainListFile.txt /path/to/testListFile.txt /path/to/outputListFile.txt
 myAlgo.sh -extract -numThreads 4 /path/to/scratch/folder /path/to/featureExtractionListFile.txt
 myAlgo.sh -TrainAndClassify -numThreads 4 /path/to/scratch/folder /path/to/trainListFile.txt /path/to/testListFile.txt /path/to/outputListFile.txt

Packaging submissions

  • All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guaranteed). IMIRSEL should be notified of any dependencies that you cannot include with your submission at the earliest opportunity (in order to give them time to satisfy the dependency).
  • Be sure to follow the Best Coding Practices for MIREX
  • Be sure to follow the MIREX 2018 Submission Instructions

All submissions should include a README file including the following the information:

  • Command line calling format for all executables including examples
  • Number of threads/cores used or whether this should be specified on the command line
  • Expected memory footprint
  • Expected runtime
  • Approximately how much scratch disk space will the submission need to store any feature/cache files?
  • Any required environments/architectures (and versions) such as Matlab, Java, Python, Bash, Ruby etc.
  • Any special notice regarding to running your algorithm

Note that the information that you place in the README file is extremely important in ensuring that your submission is evaluated properly.

Time and hardware limits

Due to the potentially high number of participants in this and other audio tasks, hard limits on the runtime of submissions will be imposed.

A hard limit of 24 hours will be imposed on feature extraction times.

A hard limit of 48 hours will be imposed on the 3 training/classification cycles, leading to a total runtime limit of 72 hours for each submission.

Potential Participants

name / email