{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:35:22Z","timestamp":1776882922740,"version":"3.51.2"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001691","name":"JSPS","doi-asserted-by":"publisher","award":["24K23880,25K21221"],"award-info":[{"award-number":["24K23880,25K21221"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001695","name":"JST","doi-asserted-by":"publisher","award":["JPMJMS2237"],"award-info":[{"award-number":["JPMJMS2237"]}],"id":[{"id":"10.13039\/501100001695","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249121","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"131-136","source":"Crossref","is-referenced-by-count":3,"title":["Human-CLAP: Human-perception-based Contrastive Language-audio Pretraining"],"prefix":"10.1109","author":[{"given":"Taisei","family":"Takano","sequence":"first","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Okamoto","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Kanamori","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryotaro","family":"Nagase","sequence":"additional","affiliation":[{"name":"Ritsumeikan University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"21450","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Liu","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref3","article-title":"Audiogen: Textually guided audio generation","volume-title":"Proc. the Eleventh International Conference on Learning Representations","author":"Kreuk","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10894"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3497586"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref7","article-title":"DCASE 2023 task 6 automated audio captioning and language-based retrieval","volume-title":"DCASE2023 Challenge, Tech. Rep.","author":"Karanth","year":"2023"},{"key":"ref8","article-title":"DCASE 2023 task 6 automated audio captioning and language-based retrieval","volume-title":"DCASE2023 Challenge, Tech. Rep.","author":"Greeshma","year":"2023"},{"key":"ref9","article-title":"DCASE 2023 task 6b: Text-to-audio retrieval using pretrained models","volume-title":"DCASE2023 Challenge, Tech. Rep.","author":"Wang","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref12","first-page":"1391613932","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"Proc. the 40th International Conference on Machine Learning","volume":"202","author":"Huang","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681688"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3485485"},{"key":"ref17","first-page":"4542","article-title":"Baton: Aligning text-to-audio model using human preference feedback","volume-title":"Proc. the Thirty-Third International Joint Conference on Artificial Intelligence","author":"Liao","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1830"},{"key":"ref20","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","volume-title":"Proc. the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Kim","year":"2019"},{"key":"ref21","article-title":"Foley sound synthesis at the DCASE 2023 challenge","volume-title":"Proc. Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)","author":"Choi","year":"2023"},{"key":"ref22","article-title":"Meta audiobox aesthetics: Unified automatic quality assessment for speech, music, and sound","author":"Tjandra","year":"2025","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832315"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref25","first-page":"87488763","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. the 38th International Conference on Machine Learning (ICML)","volume":"139","author":"Radford","year":"2021"},{"key":"ref26","article-title":"Decoupled weight decay regularization","volume-title":"Proc. International Conference on Learning Representations","author":"Loshchilov","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Singapore, Singapore","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249121.pdf?arnumber=11249121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:50:09Z","timestamp":1764399009000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249121\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249121","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}