{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:12:30Z","timestamp":1776881550223,"version":"3.51.2"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889886","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Multiple Consistency-guided Test-Time Adaptation for Contrastive Audio-Language Models with Unlabeled Audio"],"prefix":"10.1109","author":[{"given":"Gongyu","family":"Chen","sequence":"first","affiliation":[{"name":"College of Computer and Science, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haomin","family":"Zhang","sequence":"additional","affiliation":[{"name":"AI Lab, Giant Network"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaofan","family":"Ding","sequence":"additional","affiliation":[{"name":"AI Lab, Giant Network"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"Chen","sequence":"additional","affiliation":[{"name":"AI Lab, Giant Network"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhan","family":"Di","sequence":"additional","affiliation":[{"name":"AI Lab, Giant Network"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10448504"},{"key":"ref2","article-title":"Pengi: An audio language model for audio tasks","author":"Deshmukh","year":"2023"},{"key":"ref3","article-title":"Listen, think, and understand","author":"Gong","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095969"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446472"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1082"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref11","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref12","article-title":"Consistency-guided prompt learning for vision-language models","author":"Roy","year":"2023"},{"key":"ref13","article-title":"Test-time training with self-supervision for generalization under distribution shifts","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Sun"},{"key":"ref14","first-page":"21 808","article-title":"Ttt++: When does self-supervised test-time training fail or thrive?","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Liu","year":"2021"},{"key":"ref15","article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"International Conference on Learning Representations","author":"Wang"},{"key":"ref16","article-title":"Test-time training with masked autoencoders","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Gandelsman"},{"key":"ref17","first-page":"38 629","article-title":"Memo: Test time robustness via adaptation and augmentation","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Zhang","year":"2022"},{"key":"ref18","first-page":"14 274","article-title":"Test-time prompt tuning for zero-shot gen-eralization in vision-language models","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Shu","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-41"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00109"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10448115"},{"key":"ref24","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"ref25","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref26","article-title":"Hear: Holistic evaluation of audio representations","author":"Turian","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref29","first-page":"85","article-title":"DCASE 2017 challenge setup: tasks, datasets and baseline system","volume-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2017 Workshop (DCASE2017)","author":"Mesaros"},{"key":"ref30","article-title":"Automatic musical genre classification of audio signals","volume-title":"International Society for Music Information Retrieval Conference","author":"Tzanetakis"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746828"},{"key":"ref34","article-title":"Sound events for surveillance applications","author":"Spadini","year":"2019"},{"key":"ref35","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","volume-title":"Proceedings of the 34th International Conference on Machine Learning - Volume 70","author":"Engel"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889886.pdf?arnumber=10889886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:49Z","timestamp":1774416349000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889886\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889886","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}