Open Science and Reproducibility are core goals of the MTG, promoting collaborations by making sure that our research results can be used by other researchers and by society at large. Here we highlight some of the software tools and datasets developed as part of our research and that are being maintained by researchers of the MTG. All our open source projects are made available from our github repository and all our open datasets are made available from Zenodo. Please review the terms and conditions of use stated in each software tool and dataset to make sure that they allow your intended use.
Apart from research collaborations, we are also interested in technology transfer, offering commercial licenses for exploiting our technology portfolio in industrial applications. Contact us for any further information.
Software library for audio and music analysis, description, and synthesis.
Software library to apply similarity measures and classiﬁcations on the results of audio analysis.
Sound analysis/synthesis tools for music applications.
A Gaze-Controlled Digital Music Instrument.
Modular and extensible desktop application to explore the Dunya corpora.
Android app to explore and listen to a collection of Carnatic and Hindustani music.
Vamp plug-in for chroma feature extraction from polyphonic music signals.
Vamp plug-in for predominant melody estimation from polyphonic audio signals.
Vamp plug-in library in C++ which implements a basic set of descriptors useful for teaching MIR.
Platform for the collaborative creation of open audio collections from Freesound.
Data repository and visualization tool for music performance multi-modal recordings.
Library of tools for accessing and working with datasets of relevance to the field of Music Information Retrieval (MIR)
Collection of datasets related to the Dunya/Compmusic corpora.
Datasets using sounds from Freesound.
A Dataset for Cover Song Identification and Understanding.
Annotations of drum events within known music audio recordings datasets.
Multimodal recordings of string quartet performances.
Knowledge Base of flamenco music.
Key annotations of a music audio collection.
Tempo annotations of a music audio collection.
Recordings of single notes and scales played by several instruments.
Scores and harmonic annotations of Haydn's String Quartets Op. 20.
Musical audio excerpts with annotations of the predominant instruments.
ISMIR 2004 Genre Identification task dataset.
Audio-aligned jazz harmony dataset.
Knowledge Base automatically extracted from songfacts.com.
<user, artist-mbid, artist-name, total-plays> tuples from Last.fm.
Text and accompanying metadata of Amazon customer reviews.
Multi-track recordings for audio source separation research.
AcousticBrainz music features and genre/subgenre annotations extracted from AllMusic, Discogs, Lastfm and Tagtraum
Recordings of sung melodies for Query-by-Humming research.
Open dataset for the tasks of music detection and relative music loudness estimation.
Orchestral music excerpts with annotations for melody extraction research.
Denoised recordings and note annotations for Aalto anechoic orchestral database.
Excerpts of the Eroica Symphony by Beethoven plus audio descriptors.
Different Motion Capture (MoCap) recordings of conducting movements.
Multimodal data of string quartet performances.
List of artists and biographical information for semantic artist similarity research.
Flamenco a cappella sung melodies with manual transcriptions.