Audio captioning DCASE 2020 evaluation (testing) split

Open data API in a single place

Provided by Zenodo

Get early access to Audio captioning DCASE 2020 evaluation (testing) split API!

Let us know and we will figure it out for you.

Dataset information

Country of origin
Updated
2020.12.08 00:00
Created
2020.01.01
Available languages
English
Keywords
Signal processing, Computational auditory scene analysis, Clotho, Audio captioning, Machine listening, Deep learning, Dataset, Audio processing, DCASE2020, Captioning
Quality scoring

Dataset description

This is the evaluation split for Task 6, Automated Audio Captioning, in DCASE 2020 Challenge.  This evaluation split is the Clotho testing split, which is thoroughly described in the corresponding paper:  K. Drossos, S. Lipping and T. Virtanen, "Clotho: an Audio Captioning Dataset," IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020, pp. 736-740, doi: 10.1109/ICASSP40776.2020.9052990. available online at: https://arxiv.org/abs/1910.09387 and at: https://ieeexplore.ieee.org/document/9052990  This evaluation split is meant to be used for the purposes of the Task 6 at the scientific challenge DCASE 2020. This split it is not meant to be used for developing audio captioning methods. For developing audio captioning methods, you should use the development and evaluation splits of Clotho.  If you want the development and evaluation splits of Clotho dataset, you can find them also in Zenodo, at: https://zenodo.org/record/3490684 -------------------------------------------------------------------------------------------------------- == License == The audio files in the archives: clotho_audio_test.7z  and the associated meta-data in the CSV file: clotho_metadata_test.csv are under the corresponding licences (mostly CreativeCommons with attribution) of Freesound [1] platform, mentioned explicitly in the CSV file for each of the audio files. That is, each audio file in the 7z archive is listed in the CSV file with the meta-data. The meta-data for each file are:  File name Start and ending samples for the excerpt that is used in the Clotho dataset Uploader/user in the Freesound platform (manufacturer) Link to the licence of the file -------------------------------------------------------------------------------------------------------- == References == [1] Frederic Font, Gerard Roma, and Xavier Serra. 2013. Freesound technical demo. In Proceedings of the 21st ACM international conference on Multimedia (MM '13). ACM, New York, NY, USA, 411-412. DOI: https://doi.org/10.1145/2502081.2502245
European data infrastructure with broad catalog discovery, free evaluation access and production-grade API options.
190K+
indexed dataset pages
32
countries and EU institutions
2019
API-first since
Free API quota
for evaluation and prototypes
SLA
history and push on production APIs
FAQ

Questions before production use

Practical answers on evaluation, licensing, freshness, versioning and support.

api.store is built and operated by Apitalks s.r.o. Company details and a direct contact path are linked in the footer for vendor checks and procurement review.
Yes. Selected APIs include a free API quota, so your team can validate coverage, freshness, response shape and workflow fit before asking for a production plan.
Often yes, but usage rights depend on the source license and dataset. We surface source, license and update metadata where available, and can help review terms before a production integration.
Maintained APIs include update metadata where available. For production integrations, we can add history, monitoring and push updates so changes are easier to detect and act on.
Production APIs can add SLA, stable identifiers, versioning support, history, push updates and direct support around the data your product or AI workflow depends on.

Didn't find the API you need?

Let us know and we will figure it out for you.

European data discovery with free evaluation access and production-grade API options.

Copyright © 2026. Made by Apitalks