Audio and Acoustic Signal Processing
Technical Committee Online Resources
This page collects links to online resources (datasets and software tools) that are pertinent to researchers and practitioners in the area of Audio and Acoustic Signal Processing. It is conceived just as a starting point for locating this type of resources, therefore it should not by any means be intended as exhaustive. This page will be kept updated (if you wish to point out relevant missing resources, you may do so by contacting a member of the publicity subcommittee of the AASP Technical Committee).
Datasets
- Schubert Winterreise Dataset (SWD)
https://zenodo.org/record/4122060#.YPkxv-gzaUl
International Audio Laboratories Erlangen - University of Erlangen-Nuremberg, Germany - MTD: A Multimodal Dataset of Musical Themes for MIR Research
https://www.audiolabs-erlangen.de/resources/MIR/MTD
International Audio Laboratories Erlangen - University of Erlangen-Nuremberg, Germany - Dagstuhl ChoirSet
https://www.audiolabs-erlangen.de/resources/MIR/2020-DagstuhlChoirSet
International Audio Laboratories Erlangen - University of Erlangen-Nuremberg, Germany - Erkomaishvili Dataset
https://www.audiolabs-erlangen.de/resources/MIR/2019-GeorgianMusic-Erkomaishvili
International Audio Laboratories Erlangen - University of Erlangen-Nuremberg, Germany - "Dregon: Dataset and methods for UAV-embedded sound source localization."
http://dregon.inria.fr
A joint effort of FAU - Friedrich-Alexander Universität Erlangen-Nürnberg, INRIA Rennes, ENS Rennes and INRIA Nancy.
Reference paper: https://hal.inria.fr/hal-01854878/file/2018_iros_strauss.pdf - CHiME Challenge Series
http://spandh.dcs.shef.ac.uk/projects/chime/#aboutPage
The CHiME challenges are a series of automatic speech recognition evaluations targeting distant multiple microphone speech recognition in everyday listening environments. - Multi-Channel Acoustic Response Database
http://www.eng.biu.ac.il/gannot/downloads/
Measured at BIU acoustic lab in three different revberation levels (T60=160,360,610ms) and for various loudspeaker positions and microphone array configuration.
Bar-Ilan, Israel and RWTH Aachen, Germany. - Multichannel Acoustic Database Resources
http://www.commsp.ee.ic.ac.uk/~acousp/
Includes guidelines for multi-channel data annotation as well as links to annotated multi-channel datasets. - Single- and multichannel audio recordings database (SMARD)
http://www.smard.es.aau.dk/
Aalborg University, Denmark - Multichannel Acoustic Reverberation Database at York (MARDY)
http://www.commsp.ee.ic.ac.uk/~sap/resources/mardy-multichannel-acoustic-reverberation-database-at-york-database/
Speech and Audio Processing Group – Imperial College – London, UK - Aachen Impulse Response Database (AIR)
http://www.ind.rwth-aachen.de/en/research/tools-downloads/aachen-impulse-response-database/
Institute of Communication Systems and Data Processing - RWTH Aachen University, Germany - Room Impulse Response Data Set
http://isophonics.net/content/room-impulse-response-data-set
Center for Digital Music (C4DM) – Queen Mary University of London, UK - Open Acoustic Impulse Response (Open AIR) Library
http://www.openairlib.net
University of York, UK - Datasets on Environmental Sounds
http://www.cs.tut.fi/~heittolt/datasets#online-services
Dataset that are suitable for environmental audio research - Database of multichannel in-ear and behind-the-ear head-related and binaural room impulse responses
http://medi.uni-oldenburg.de/hrir/
Department of Medical Physics and Acoustics, Carl-von-Ossietzky University, Oldenburg, Germany - QUASI Music Source Separation Database
http://www.tsi.telecom-paristech.fr/aao/en/2012/03/12/quasi/
A musical audio signal database for source separation.
Groupe AAO - Audio, Acoustique et Ondes, Telecom ParisTec, France
Software resources and tools
- Python package "libfmp"
https://github.com/meinardmueller/libfmp
International Audio Laboratories Erlangen - University of Erlangen-Nuremberg, Germany
This repository contains the Python package libfmp. This package goes hand in hand with the FMP Notebooks, a collection of educational material for teaching and learning Fundamentals of Music Processing (FMP) with a particular focus on the audio domain. - Python package "Sync Toolbox"
https://github.com/meinardmueller/synctoolbox
International Audio Laboratories Erlangen - University of Erlangen-Nuremberg, Germany
This repository contains a Python package called Sync Toolbox, which provides open-source reference implementations for full-fledged music synchronization pipelines and yields state-of-the-art alignment results for a wide range of Western music. - Python package "libtsm"
A Python toolbox for Time-Scale Modification (TSM) and Pitch-Shifting.
https://github.com/meinardmueller/libtsm
International Audio Laboratories Erlangen - University of Erlangen-Nuremberg, Germany - NMF Toolbox
The toolbox is available both for MATLAB and Python.
https://www.audiolabs-erlangen.de/resources/MIR/NMFtoolbox
International Audio Laboratories Erlangen - University of Erlangen-Nuremberg, Germany - RIR Generator (to generate room impulse responses)
http://www.audiolabs-erlangen.de/fau/professor/habets/software/rir-generator
International Audio Laboratories Erlangen - University of Erlangen-Nuremberg, Germany - Signal Generator (to simulate moving sources)
http://www.audiolabs-erlangen.de/fau/professor/habets/software/signal-generator
International Audio Laboratories Erlangen - University of Erlangen-Nuremberg, Germany - Spherical Microphone array Impulse Response generator (SMIRgen)
http://www.audiolabs-erlangen.de/fau/professor/habets/software/smir-generator
International Audio Laboratories Erlangen - University of Erlangen-Nuremberg, Germany - Noise Generators (to generate sensor signals in isotropic noise fields, nonstationary multi-sensor signals under a spatial coherence constraint, multi-channel babble speech signals, and multi-channel wind noise)
http://www.audiolabs-erlangen.de/fau/professor/habets/software/noise-generators
International Audio Laboratories Erlangen - University of Erlangen-Nuremberg, Germany - Spherical Microphone array Impulse Response for Directional source generator (SMIRDgen)
http://www.commsp.ee.ic.ac.uk/~ssh12/SMIRD.htm
Speech and Audio Processing Group – Imperial College – London, UK - Room Impulse Response for Directional source generator (RIRDgen)
http://www.commsp.ee.ic.ac.uk/~ssh12/RIRD.htm
Speech and Audio Processing Group – Imperial College – London, UK - BSS Locate - A toolbox for source localization in stereo convolutive audio mixtures
http://bass-db.gforge.inria.fr/bss_locate/
INRIA- Paris, France - VOICEBOX: Speech Processing Toolbox for MATLAB
http://www.ee.ic.ac.uk/hp/staff/dmb/voicebox/voicebox.html
Department of Electrical & Electronic Engineering, Imperial College, London, UK - Speaker Identification on YOHO
http://www.commsp.ee.ic.ac.uk/~jg/publicationlist#softwareLab
Speech and Audio Processing Group – Imperial College - London, UK - FASST - Flexible Audio Source Separation Toolbox (2012)
http://bass-db.gforge.inria.fr/fasst/
INRIA – Paris, France - Multichannel nonnegative matrix factorization toolbox (2010)
http://www.irisa.fr/metiss/ozerov/Software/multi_nmf_toolbox.zip
INRIA – Paris, France - Audio source separation using full-rank spatial covariance model (2010)
http://www.irisa.fr/metiss/ngoc/sw/bss-fullrank.rar
INRIA – Paris, France - BSS Eval toolbox for performance measurement (2008)
http://bass-db.gforge.inria.fr/bss_eval/
INRIA – Paris, France
