Recap: Retrieval-Augmented Audio Captioning
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
We present RECAP (REtrieval-Augmented Audio CAPtioning), a novel and effective audio captioning system that generates captions conditioned on an input audio and other captions similar to the audio retrieved from a datastore. Additionally, our proposed method can transfer to any domain without the need for any additional fine-tuning. To generate a caption for an audio sample, we leverage an audio-text model CLAP [1] to retrieve captions similar to it from a replaceable datastore, which are then used to construct a prompt. Next, we feed this prompt to a GPT-2 decoder and introduce cross-attention layers between the CLAP encoder and GPT-2 to condition the audio for caption generation. Experiments on two benchmark datasets, Clotho and AudioCaps, show that RECAP achieves competitive performance in in-domain settings and significant improvements in out-of-domain settings. Additionally, due to its capability to exploit a large text-captions-only datastore in a training-free fashion, RECAP shows unique capabilities of captioning novel audio events never seen during training and compositional audios with multiple events. To promote research in this space, we also release 150,000+ new weakly labeled captions for AudioSet, AudioCaps, and Clotho1.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
In the citing paper
“For RECAP, captions are included into LLM prompts, while [43] uses both audio and retrieved captions in attention module.”
From Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024) · cites this paper as [323]
In the citing paper
“RECAP [323] and [43] leverages dense retrievers, CLAP [26] and VGGish [69] respectively, to retrieve related captions given audio data.”
From Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024) · cites this paper as [323]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.11401 · Cited by 3,101
Natural Questions: A benchmark for question answering research
Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., et al. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00276 · Cited by 2,069
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 3×
“However, we introduce three novel changes: (1) Instead of employing an audio encoder pre-trained only on audio, we use CLAP [1] as our audio encoder.”
BackgroundMethodInfluentialClotho: an Audio Captioning Dataset
Drossos, K., Lipping, S., & Virtanen, T. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9052990 · Cited by 285 · cited 8×
“Compared to Automatic Speech Recognition (ASR), which tran-scribes human speech, audio captioning focuses on describing distinct environmental sounds in the input audio [2, 3].”
BackgroundMethodInfluentialAtlas: Few-shot Learning with Retrieval Augmented Language Models
Izacard, G., Lewis, P., Lomeli, M., Hosseini, L., Petroni, F., Schick, T., Dwivedi-Yu, J., Joulin, A., Riedel, S., & Grave, E. (2022) · arXiv · doi:10.48550/arxiv.2208.03299 · Cited by 213
AudioCaps: Generating Captions for Audios in The Wild
Kim, C. D., Kim, B., Lee, H., & Kim, G. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1011 · Cited by 96
Research works printed but not linked: 14
- 10.1109/TMM.2022.3149712 · DOI · Paper page
- Gontier, 2021, Automated audio captioning by fine-tuning bart with audioset tags, DCASE2021 Challenge
- 10.1109/ICASSP49357.2023.10096877 · DOI · Paper page
- 10.1109/ISM.2020.00014 · DOI
- 10.1109/ICASSP39728.2021.9413982 · DOI
- Wu, Beats-based audio captioning model with instructor embedding supervision and chatgpt mix-up
- Sun, Leveraging multi-task training and image retrieval with clap for audio captioning
- Sim, Label-refined sequential training with noisy data for automated audio captioning
- Berant, Semantic parsing on freebase from question-answer pairs, EMNLP 2013, 1533
- 10.1145/3549555.3549585 · DOI · Paper page
- 10.18653/v1/2023.eacl-main.266 · DOI · Paper page
- Mei, Audio captioning transformer, DCASE2021 Challenge.
- Chen, 2020, Audio captioning based on transformer and pre-trained cnn, DCASE, 21
- 10.1109/ICASSP43922.2022.9747676 · DOI
Cited by
Retrieval-Augmented Generation for AI-Generated Content: A Survey
Zhao, P., Zhang, H., Yu, Q., Wang, Z., Geng, Y., Fu, F., Yang, L., Zhang, W., Jiang, J., & Cui, B. (2024) · arXiv · doi:10.48550/arxiv.2402.19473 · Cited by 240
Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation
Abootorabi, M. M., Zobeiri, A., Dehghani, M., Mohammadkhani, M., Mohammadi, B., Ghahroodi, O., Baghshah, M. S., & Asgari, E. (2025) · Findings of the Association for Computational Linguistics: ACL 2025 · doi:10.18653/v1/2025.findings-acl.861 · Cited by 76
Metadata
- Authors
- Ghosh, S., Kumar, S., Reddy Evuru, C. K., Duraiswami, R., & Manocha, D.
- Affiliations
- University of Maryland,College Park,USA
- Venue
- ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2024-04-14
- Pages
- 1161-1165
- Cited by
- 21
- References
- 7
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Recap: Retrieval-Augmented Audio Captioning. https://app.cochat.ai/papers/10.1109/icassp48485.2024.10448030
- The paper
- Ghosh, S., Kumar, S., Reddy Evuru, C. K., Duraiswami, R., & Manocha, D. (2024). Recap: Retrieval-Augmented Audio Captioning. ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp48485.2024.10448030
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.