Papers › EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated...

EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning

31 Jan 2024arXiv:2401.17690archive 2025-07-28

Jaeyeon Kim, JaeYoon Jung, Jinjoo Lee, Sang Hoon Woo

We propose EnCLAP, a novel framework for automated audio captioning. EnCLAP employs two acoustic representation models, EnCodec and CLAP, along with a pretrained language model, BART. We also introduce a new training objective called masked codec modeling that improves acoustic awareness of the pretrained language model. Experimental results on AudioCaps and Clotho demonstrate that our model surpasses the performance of baseline models. Source code will be available at https://github.com/jaeyeonkim99/EnCLAP . An online demo is available at https://huggingface.co/spaces/enclap-team/enclap .

PaperPDFCode

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.

Code

jaeyeonkim99/enclap officialmentioned in papermentioned on GitHubpytorchMIT 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Audio captioningLanguage ModelingLanguage Modelling

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Audio captioning AudioCaps EnCLAP-large CIDEr 0.8029 #8 of 18 Archive leaderboard report
Audio captioning AudioCaps EnCLAP-large METEOR 0.2554 #8 of 18 Archive leaderboard report
Audio captioning AudioCaps EnCLAP-large SPICE 0.1879 #8 of 18 Archive leaderboard report
Audio captioning AudioCaps EnCLAP-large SPIDEr 0.4954 #8 of 18 Archive leaderboard report
Audio captioning AudioCaps EnCLAP-base CIDEr 0.7795 #10 of 18 Archive leaderboard report
Audio captioning AudioCaps EnCLAP-base METEOR 0.2473 #10 of 18 Archive leaderboard report
Audio captioning AudioCaps EnCLAP-base SPICE 0.1863 #10 of 18 Archive leaderboard report
Audio captioning AudioCaps EnCLAP-base SPIDEr 0.4829 #10 of 18 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.

Methods

AdamAttentionBARTBPEDense ConnectionsDropoutLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmax

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