Song Describer Dataset

DOI

The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation.

A retro-futurist drum machine groove drenched in bubbly synthetic sound effects and a hint of an acid bassline.

The Song Describer Dataset (SDD) contains ~1.1k captions for 706 permissively licensed music recordings. It is designed for use in evaluation of models that address music-and-language (M&L) tasks such as music captioning, text-to-music generation and music-language retrieval. More information about the data, collection method and validation is provided in the paper describing the dataset.

If you use this dataset, please cite our paper:

The Song Describer Dataset: a Corpus of Audio Captions for Music-and-Language Evaluation, Manco, Ilaria and Weck, Benno and Doh, Seungheon and Won, Minz and Zhang, Yixiao and Bogdanov, Dmitry and Wu, Yusong and Chen, Ke and Tovstogan, Philip and Benetos, Emmanouil and Quinton, Elio and Fazekas, György and Nam, Juhan, Machine Learning for Audio Workshop at NeurIPS 2023, 2023

Identifier
DOI https://doi.org/10.34810/DATA2630
Metadata Access https://dataverse.csuc.cat/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=doi:10.34810/DATA2630
Provenance
Creator Manco, Ilaria ORCID logo; Weck, Benno ORCID logo; Bogdanov, Dmitry ORCID logo; Tovstogan, Philip ORCID logo; Won, Minz ORCID logo
Publisher CORA.Repositori de Dades de Recerca
Contributor WECK-HUFNAGEL, BENNO; Music Technology Group; UKRI Centre for Doctoral Training in Artificial Intelligence and Music; Universitat Pompeu Fabra
Publication Year 2025
Funding Reference Agencia Estatal de Investigación PID2019-111403GB-I0
Rights CC BY-SA 4.0; info:eu-repo/semantics/openAccess; http://creativecommons.org/licenses/by-sa/4.0
OpenAccess true
Contact WECK-HUFNAGEL, BENNO (Universitat Pompeu Fabra); Music Technology Group (Universitat Pompeu Fabra)
Representation
Resource Type Machine-readable text; Dataset
Format audio/mpeg; application/octet-stream; text/plain; text/tab-separated-values; application/pdf; text/tsv
Size 4801005; 4801351; 3746004; 3482925; 4508779; 3833775; 4781498; 4801641; 4801528; 2003114; 5906274; 5906285; 3601808; 4582125; 4801412; 4801065; 3914925; 4801422; 2532877; 3762722; 3878706; 4801402; 4655065; 4447130; 1248698; 4552665; 2497351; 1360502; 2081481; 4182771; 2491081; 4801608; 2617514; 4727163; 4801530; 2482722; 4801459; 4801873; 4801919; 4801875; 4351000; 4559979; 4801538; 4801545; 4801537; 4801542; 4037530; 4115898; 2621694; 3758543; 4582967; 2823359; 4550575; 4368763; 4801471; 4801427; 4137841; 4026036; 4111718; 4801456; 4801782; 4759555; 3401187; 4801509; 4480567; 2674983; 4801448; 4501465; 2678118; 249904; 162171; 107394; 204200; 5698; 5746; 11546; 5743; 5737; 5755; 5683; 11449; 64685; 108663; 10214; 9683; 191731; 41634
Version 1.0
Discipline Fine Arts, Music, Theatre and Media Studies; Humanities; Music