JamendoMaxCaps: A Large Scale Music-caption Dataset with Imputed Metadata
Open accessAbstract
We introduce JamendoMaxCaps, a large-scale music-caption dataset featuring over 362,000 freely licensed instrumental tracks from the renowned Jamendo platform. The dataset includes captions generated by a state-of-the-art captioning model, enhanced with imputed metadata. We also introduce a retrieval system that leverages both musical features and metadata to identify similar songs, which are then used to fill in missing metadata using a local large language model (LLLM). This approach allows us to provide a more comprehensive and informative dataset for researchers working on music-language understanding tasks. We validate this approach quantitatively with five different measurements. By making the JamendoMaxCaps dataset publicly available, we provide a high-quality resource to advance research in music-language understanding tasks such as music retrieval, multimodal representation learning, and generative music models.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The largest open-source dataset with music and matching text captions is JamendoMaxCaps, containing over 362k songs.
“Currently, the largest opensource dataset with music and matching text captions is JamendoMaxCaps Roy et al. (2025), which contains over 362k songs.”
From SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning (2025) · cites this paper as Roy et al., 2025
Music captioning remains an open challenge due to the lack of an extensive dataset.
“Ironically, this task remains an open challenge due to the lack of an extensive dataset.”
From SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning (2025) · cites this paper as Roy et al., 2025
Cites
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344 · see citing works
PsyToolkit: A software package for programming psychological experiments using Linux
Stoet, G. (2010) · Behavior Research Methods · doi:10.3758/brm.42.4.1096 · Cited by 1,274 · see citing works
A Survey on In-context Learning
Dong, Q., Li, L., Dai, D., Zheng, C., Ma, J., Li, R., Xia, H., Xu, J., Wu, Z., Chang, B., et al. (2024) · Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2024.emnlp-main.64 · Cited by 649 · see citing works
Wu, Y., Chen, K., Zhang, T., Hui, Y., Berg-Kirkpatrick, T., & Dubnov, S. (2023) · ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp49357.2023.10095969 · Cited by 459 · cited 1× · see citing works
“In the sound/speech domain, we find several expansive datasets such as LAION-Audio [26] and wav2vec [18], each comprising over 500,000 audio-caption pairs.”
CLAP Learning Audio Concepts from Natural Language Supervision
Elizalde, B., Deshmukh, S., Ismail, M. A., & Wang, H. (2023) · ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp49357.2023.10095889 · Cited by 449 · see citing works
Mei, X., Meng, C., Liu, H., Kong, Q., Ko, T., Zhao, C., Plumbley, M. D., Zou, Y., & Wang, W. (2024) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2024.3419446 · Cited by 150 · see citing works
Video2Music: Suitable music generation from videos using an Affective Multimodal Transformer model
Kang, J., Poria, S., & Herremans, D. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123640 · Cited by 58 · see citing works
Self-citationMustango: Toward Controllable Text-to-Music Generation
Melechovsky, J., Guo, Z., Ghosal, D., Majumder, N., Herremans, D., & Poria, S. (2024) · Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · doi:10.18653/v1/2024.naacl-long.459 · Cited by 48 · see citing works
Self-citationSunoCaps: A novel dataset of text-prompt based AI-generated music with emotion annotations
Civit, M., Drai-Zerbib, V., Lizcano, D., & Escalona, M. J. (2024) · Data in Brief · doi:10.1016/j.dib.2024.110743 · Cited by 16 · see citing works
Missing Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models
Kim, D., & Kim, T. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73016-0_11 · Cited by 12 · see citing works
Text2midi: Generating Symbolic Music from Captions
Bhandari, K., Roy, A., Wang, K., Puri, G., Colton, S., & Herremans, D. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i22.34516 · Cited by 6 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Aligning Generative Music AI with Human Preferences: Methods and Challenges
Herremans, D., & Roy, A. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i46.41323 · Cited by 1 · see citing works
Self-citationSonicVerse: Multi-Task Learning for Music Feature-Informed Captioning
Chopra, A., Roy, A., & Herremans, D. (2025) · arXiv · doi:10.48550/arxiv.2506.15154
“Currently, the largest open-source dataset with music and matching text captions is JamendoMaxCaps Roy et al. (2025), which contains over 362k songs.”
Self-citationData-Efficient Music Captioning Via Contrastive and Semantic Alignment
Kim, L., & Park, J. (2025) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc65261.2025.11249411
Beyond Musical Descriptors: Extracting Preference-Bearing Intent in Music Queries
Baranes, M., Hennequin, R., & Epure, E. V. (2026) · Proceedings of the 4th Workshop on NLP for Music and Audio (NLP4MusA 2026) · doi:10.18653/v1/2026.nlp4musa-1.4
Rethinking Music Captioning with Music Metadata LLMS
Bukey, I., Wang, Z., Donahue, C., & Bryan, N. J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464125
FIGMA: Towards FIne-Grained Music retrievAl
Anand, N., Seth, A., Ghosh, S., Manocha, D., & Ramani Duraiswami, B. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.2197
Jamendo-MT-QA: A Benchmark for Multi-Track Comparative Music Question Answering
Koh, J., Lee, J., Kim, S. Y., Choi, G. H., Koh, J. I., Phillips, J., Lee, Y., & Song, M. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.125
- Authors
- Roy, A., Liu, R., Lu, T., & Herremans, D.
- Affiliations
- Singapore University of Technology and Design (SG)
- Venue
- 2025 International Joint Conference on Neural Networks (IJCNN)
- Publisher
- IEEE
- Published
- 2025-06-30
- Pages
- 1-8
- ISSN
- 2161-4407 (ISSN-L)
- OpenAlex
- W4416251578
- Cited by
- 2
- References
- 11
- Citations by year
- 2026: 1 · 2025: 1
- FWCI
- 1.88
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- International Joint Conference on Neural Networks (IJCNN) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- Ministry of Education, India
- Singapore University of Technology and Design
- Topics
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Music Technology and Sound Studies
- Keywords
- music captioning, instrumental music, music information retrieval, large language models, multimodal representation learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
