{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:08:41Z","timestamp":1775200121450,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434742","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["ProtoCLAP \u2013 Prototypical Contrastive Language-Audio Pretraining"],"prefix":"10.1109","author":[{"given":"Adria","family":"Mallol-Ragolta","sequence":"first","affiliation":[{"name":"Technical University of Munich University Hospital,CHI – Chair of Health Informatics,Germany"}]},{"given":"Bj\u00f6rn","family":"Schuller","sequence":"additional","affiliation":[{"name":"Technical University of Munich University Hospital,CHI – Chair of Health Informatics,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447215"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1315"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC48229.2022.9871125"},{"key":"ref6","first-page":"11","article-title":"Prototypical networks for fewshot learning","volume-title":"Proceedings of the 31st Annual Conference on Neural Information Processing Systems.","author":"Snell"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2022.108799"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/IberSPEECH.2024-27"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/IberSPEECH.2024-45"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref11","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning.","author":"Radford"},{"key":"ref12","first-page":"2594","article-title":"ProtoCLIP: Vision-Language Prototypical Network for Few-Shot Learning","volume-title":"Proceedings of the International Conference on Intelligent Robots and Systems.","author":"Jaykumar"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3335859"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1438"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2768"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747188"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref18","first-page":"12449","article-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","volume-title":"Proceedings of the 34th Conference on Neural Information Processing Systems.","author":"Baevski"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-460"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2038"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-60278-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-414"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-234"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3458754"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434742.pdf?arnumber=11434742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:05Z","timestamp":1775192345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434742\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434742","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}