Papers › Zero-shot audio captioning with audio-language model guidance and audio context keywords

Zero-shot audio captioning with audio-language model guidance and audio context keywords

14 Nov 2023arXiv:2311.08396archive 2025-07-28

Leonard Salewski, Stefan Fauth, A. Sophia Koepke, Zeynep Akata

Zero-shot audio captioning aims at automatically generating descriptive textual captions for audio content without prior training for this task. Different from speech recognition which translates audio content that contains spoken language into text, audio captioning is commonly concerned with ambient sounds, or sounds produced by a human performing an action. Inspired by zero-shot image captioning methods, we propose ZerAuCap, a novel framework for summarising such general audio signals in a text caption without requiring task-specific training. In particular, our framework exploits a pre-trained large language model (LLM) for generating the text which is guided by a pre-trained audio-language model to produce captions that describe the audio content. Additionally, we use audio context keywords that prompt the language model to generate text that is broadly relevant to sounds. Our proposed framework achieves state-of-the-art results in zero-shot audio captioning on the AudioCaps and Clotho datasets. Our code is available at https://github.com/ExplainableML/ZerAuCap.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2311.08396")

Code

Syntology Ran 13 of 17 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 13 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

explainableml/zeraucap officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

17 samples harvested; 13 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

13ran
4unverified

Licence: 17 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from explainableml/zeraucap. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

batch explainableml/zeraucap/audio_captioning/sound_obj_generator.py official repository ran fingerprinted no licence file found · pointer only · 393efe21b22bf554 · report
build_mask_matrix explainableml/zeraucap/audio_captioning/language_model/loss_func.py official repository ran no licence file found · pointer only · 5b343139acd21835 · report
clean_chat_gpt_response explainableml/zeraucap/audio_captioning/sound_obj_generator.py official repository ran no licence file found · pointer only · 7eedca5ad3fd9e77 · report
compute_valid_token_num explainableml/zeraucap/audio_captioning/language_model/loss_func.py official repository ran fingerprinted no licence file found · pointer only · 961114eca9f332c1 · report
contrastive_loss explainableml/zeraucap/audio_captioning/language_model/loss_func.py official repository ran no licence file found · pointer only · dbe18b03333fa2bc · report
get_chat_gpt_answers explainableml/zeraucap/audio_captioning/sound_obj_generator.py official repository ran no licence file found · pointer only · 46798ca8cd2b7123 · report
get_prompt_id explainableml/zeraucap/audio_captioning/inference_magic.py official repository ran no licence file found · pointer only · 583f7e4fab57b315 · report
load_AudioClip explainableml/zeraucap/audio_captioning/clip/load_clip_model.py official repository ran no licence file found · pointer only · 01cd1d45e20261ed · report
load_CLAP explainableml/zeraucap/audio_captioning/clip/load_clip_model.py official repository ran no licence file found · pointer only · 8c75381e91da6e52 · report
parse_prompt explainableml/zeraucap/audio_captioning/language_model/utlis.py official repository ran fingerprinted no licence file found · pointer only · 56d5003b7ee3900b · report
sorting_function_keyword_lists explainableml/zeraucap/audio_captioning/evaluation/join_test_results.py official repository ran fingerprinted no licence file found · pointer only · 1d8ca634885a9ffb · report
top_k_top_p_filtering explainableml/zeraucap/audio_captioning/language_model/utlis.py official repository ran no licence file found · pointer only · 96370a572229a5a9 · report
typical_filtering explainableml/zeraucap/audio_captioning/language_model/utlis.py official repository ran no licence file found · pointer only · 315ad037a2faafbf · report
load_WavCaps explainableml/zeraucap/audio_captioning/clip/load_clip_model.py official repository unverified no licence file found · pointer only · 6e5afc29fdf09196 · report
preprocess_for_AudioCLIP explainableml/zeraucap/audio_captioning/clip/audio_preprocessors.py official repository unverified no licence file found · pointer only · 5dc63fbe479018d6 · report
preprocess_for_CLAP explainableml/zeraucap/audio_captioning/clip/audio_preprocessors.py official repository unverified no licence file found · pointer only · f57277edc12fc6dc · report
preprocess_for_WavCaps explainableml/zeraucap/audio_captioning/clip/audio_preprocessors.py official repository unverified no licence file found · pointer only · 089cf8fe536c8934 · report

Tasks

Audio captioningDescriptiveImage CaptioningLanguage ModelingLanguage ModellingLarge Language ModelSpeech RecognitionZero-shot Audio Captioningspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Zero-shot Audio Captioning AudioCaps ZerAuCap BLEU-4 6.8 #2 of 4 Archive leaderboard report
Zero-shot Audio Captioning AudioCaps ZerAuCap CIDEr 28.1 #2 of 4 Archive leaderboard report
Zero-shot Audio Captioning AudioCaps ZerAuCap METEOR 12.3 #2 of 4 Archive leaderboard report
Zero-shot Audio Captioning AudioCaps ZerAuCap ROUGE-L 33.1 #2 of 4 Archive leaderboard report
Zero-shot Audio Captioning AudioCaps ZerAuCap SPICE 8.6 #2 of 4 Archive leaderboard report
Zero-shot Audio Captioning AudioCaps ZerAuCap SPIDEr 18.3 #2 of 4 Archive leaderboard report
Zero-shot Audio Captioning AudioCaps No audio (baseline) BLEU-4 0 #4 of 4 Archive leaderboard report
Zero-shot Audio Captioning AudioCaps No audio (baseline) CIDEr 0.1 #4 of 4 Archive leaderboard report
Zero-shot Audio Captioning AudioCaps No audio (baseline) METEOR 4.1 #4 of 4 Archive leaderboard report
Zero-shot Audio Captioning AudioCaps No audio (baseline) ROUGE-L 17.8 #4 of 4 Archive leaderboard report
Zero-shot Audio Captioning AudioCaps No audio (baseline) SPICE 0 #4 of 4 Archive leaderboard report
Zero-shot Audio Captioning AudioCaps No audio (baseline) SPIDEr 0 #4 of 4 Archive leaderboard report
Zero-shot Audio Captioning Clotho ZerAuCap BLEU-4 2.9 #1 of 1 Archive leaderboard report
Zero-shot Audio Captioning Clotho ZerAuCap CIDEr 14 #1 of 1 Archive leaderboard report
Zero-shot Audio Captioning Clotho ZerAuCap METEOR 9.4 #1 of 1 Archive leaderboard report
Zero-shot Audio Captioning Clotho ZerAuCap ROUGE-L 25.4 #1 of 1 Archive leaderboard report
Zero-shot Audio Captioning Clotho ZerAuCap SPICE 5.3 #1 of 1 Archive leaderboard report
Zero-shot Audio Captioning Clotho ZerAuCap SPIDEr 9.7 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections