Papers › Clotho: An Audio Captioning Dataset

Clotho: An Audio Captioning Dataset

21 Oct 2019arXiv:1910.09387archive 2025-07-28

Konstantinos Drossos, Samuel Lipping, Tuomas Virtanen

Audio captioning is the novel task of general audio content description using free text. It is an intermodal translation task (not speech-to-text), where a system accepts as an input an audio signal and outputs the textual description (i.e. the caption) of that signal. In this paper we present Clotho, a dataset for audio captioning consisting of 4981 audio samples of 15 to 30 seconds duration and 24 905 captions of eight to 20 words length, and a baseline method to provide initial results. Clotho is built with focus on audio content and caption diversity, and the splits of the data are not hampering the training or evaluation of methods. All sounds are from the Freesound platform, and captions are crowdsourced using Amazon Mechanical Turk and annotators from English speaking countries. Unique words, named entities, and speech transcription are removed with post-processing. Clotho is freely available online (https://zenodo.org/record/3490684).

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 21 code samples harvested from 2 repositories linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 21 samples from 2 repositories, 19 ran (16 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 19 samples that ran has no recorded date.

akoepke/audio-retrieval-benchmark mentioned on GitHubpytorchSyntology: not harvested report
audio-captioning/clotho-dataset mentioned on GitHubNOASSERTIONSyntology: not harvested report
dr-costas/clotho-baseline-dataset mentioned on GitHubNOASSERTIONSyntology: not harvested report
labbeti/aac-datasets mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for... (arXiv:2303.17395; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
oncescuandreea/audio-retrieval mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Audio Retrieval with Natural Language Queries (arXiv:2105.02192; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
richermans/AudioCaption mentioned on GitHubpytorchMITSyntology: 7 samples, 6 ran (0 instrument-failed) · 1 unverified report
wsntxxn/AudioCaption mentioned on GitHubpytorchMITSyntology: 14 samples, 13 ran (3 instrument-failed) · 1 unverified 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

21 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
16ran
2unverified

Licence: 5 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

richermans/AudioCaption community (archive-listed) 7 samples, 6 ran (0 instrument-failed) · 1 unverified
coco_score utils/human_eval.py ran MIT (permissive) · 42b965c67572da92 · report fixture: signature refs:dict/0/?, scorer:MockScorer/0/? · returned ndarray · level recorded 2026-09-25
collate_fn in 500 papers datasets/SJTUDataSet.py ran MIT (permissive) · 47fe80f824147b4d · report fixture: signature length_idxs:set/0/? · returned function · level recorded 2026-09-25
open_or_fd utils/kaldi_io.py ran MIT (permissive) here; the stored copy is pointer only · df07b4faa7609d90 · report fixture: signature file:str/0/str, mode:str/0/str · returned BufferedReader · level recorded 2026-09-24
parse_poolingfunction models/encoder.py ran MIT (permissive) · c26450c99bacd017 · report fixture: signature poolingfunction_name:str/0/str, inputdim:int/0/int, outputdim:int/0/int · returned AttentionPool · level recorded 2026-09-25
popen utils/kaldi_io.py ran MIT (permissive) here; the stored copy is pointer only · d9a4862872e34aad · report fixture: signature cmd:str/0/str, mode:str/0/str · returned BufferedReader · level recorded 2026-09-24
read_key utils/kaldi_io.py ran MIT (permissive) here; the stored copy is pointer only · aa10e48fc468d9e0 · report fixture: signature fd:BytesIO/0/? · returned str · level recorded 2026-09-24
build_vocab in 36 papers utils/build_vocab.py unverified MIT (permissive) · ef7046e8db3256f6 · report
wsntxxn/AudioCaption community (archive-listed) 14 samples, 13 ran (3 instrument-failed) · 1 unverified
NAME_TO_WIDTH captioning/models/eff_at_encoder.py ran fingerprinted MIT (permissive) · 36732bf2fa117007 · report fixture: signature name:str/0/str · returned float · level recorded 2026-09-24
cnn_out_size captioning/models/eff_at_encoder.py ran MIT (permissive) · 96fd7d5df7f15091 · report fixture: signature in_size:int/0/int, padding:int/0/int, dilation:int/0/int, kernel:int/0/int, stride:int/0/int · returned int · level recorded 2026-09-24
conv_conv_block captioning/models/crnn_trm_encoder.py ran MIT (permissive) · 7c55804fff5d4cc0 · report fixture: signature in_channel:int/0/int, out_channel:int/0/int · returned Sequential · level recorded 2026-09-24
cs_interspeech captioning/models/conv_filter_pruning.py ran MIT (permissive) · 8ebc0d04df3640f5 · report fixture: signature Z:ndarray/4/float · returned list · level recorded 2026-09-24
generate_length_mask captioning/models/flops_counting_model.py ran MIT (permissive) · 99b3ce923e424db3 · report fixture: signature lens:list/1/int, max_length:NoneType/0/? · returned Tensor · level recorded 2026-09-24
gumbel_softmax_sample in 49 papers
census: 14 implementations from 16 papers, 4 distinct outputs on one shared input
captioning/losses/loss.py ran fingerprinted MIT (permissive) · e698f855f3588740 · report fixture: signature logit:Tensor/2/float, temperature:float/0/float · returned Tensor · level recorded 2026-09-24
make_divisible in 76 papers captioning/models/eff_at_encoder.py ran MIT (permissive) · 9e10f323aeefe252 · report fixture: signature v:float/0/float, divisor:int/0/int, min_value:NoneType/0/? · returned int · level recorded 2026-09-24
operator_norm_pruning captioning/models/conv_filter_pruning.py ran MIT (permissive) · 18d5889c7ea06109 · report fixture: signature weight:ndarray/4/float · returned ndarray · level recorded 2026-09-24
pad_unsort_packed_sequence in 13 papers captioning/models/hf_wrapper.py ran · our draft was wrong MIT (permissive) · bfac58a04b6835f5 · report fixture: signature input:PackedSequence/1/Tensor, inv_ix:Tensor/1/int · returned Tensor · level recorded, date not recorded
rank1_apporx captioning/models/conv_filter_pruning.py ran fingerprinted MIT (permissive) · 0fac7426325be231 · report fixture: signature data:ndarray/2/float · returned ndarray · level recorded 2026-09-24
reparameterize_argmax captioning/losses/loss.py ran fingerprinted MIT (permissive) · 5ead97ccfc2dee7b · report fixture: signature logit:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-24
sample_gumbel in 62 papers captioning/losses/loss.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 2908a8bdfec77e29 · report fixture: signature shape:tuple/1/int, eps:float/0/float · returned Tensor · level recorded 2026-09-22
sort_pack_padded_sequence in 13 papers captioning/models/hf_wrapper.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 86839e01585b85d8 · report fixture: signature input:Tensor/3/float, lengths:Tensor/1/int · returned tuple · level recorded 2026-09-24
pack_wrapper in 13 papers captioning/models/hf_wrapper.py unverified MIT (permissive) · 471b42e75608e3d8 · report

Tasks

Audio captioningDiversitySpeech-to-TextTranslation

Datasets

Introduced by this paper, per the archive.

Clotho

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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