{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T22:06:37Z","timestamp":1779228397338,"version":"3.51.4"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2025-00557944"],"award-info":[{"award-number":["RS-2025-00557944"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002486","name":"Hankuk University of Foreign Studies","doi-asserted-by":"publisher","award":["Of 2025"],"award-info":[{"award-number":["Of 2025"]}],"id":[{"id":"10.13039\/501100002486","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute of Information & Communications Technology Planning & Evaluation","doi-asserted-by":"publisher","award":["IITP-2026-RS-2023-00253914"],"award-info":[{"award-number":["IITP-2026-RS-2023-00253914"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Speech & Language"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.csl.2026.101947","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T18:59:43Z","timestamp":1769713183000},"page":"101947","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Bumper-guided representation interpolation for black-box unsupervised domain adaptation"],"prefix":"10.1016","volume":"100","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5485-8944","authenticated-orcid":false,"given":"Jin-Seong","family":"Choi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jae-Hong","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2610-2323","authenticated-orcid":false,"given":"Joon-Hyuk","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.csl.2026.101947_b1","unstructured":"Adam, K.D.B.J., et al., 2014. Adam: A method for stochastic optimization. In: Proc. International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.csl.2026.101947_b2","series-title":"Proc. International Joint Conference on Neural Networks","first-page":"1","article-title":"Pseudo-labeling and confirmation bias in deep semi-supervised learning","author":"Arazo","year":"2020"},{"key":"10.1016\/j.csl.2026.101947_b3","series-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019"},{"key":"10.1016\/j.csl.2026.101947_b4","unstructured":"Athiwaratkun, B., Finzi, M., Izmailov, P., Wilson, A.G., 2018. There are many consistent explanations of unlabeled data: Why you should average. In: Proc. International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.csl.2026.101947_b5","unstructured":"Athiwaratkun, B., Finzi, M., Izmailov, P., Wilson, A.G., 2021. Momentum pseudo-labeling for semi-supervised speech recognition. In: Proc. INTERSPEECH."},{"key":"10.1016\/j.csl.2026.101947_b6","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"vol. 33","author":"Baevski","year":"2020"},{"key":"10.1016\/j.csl.2026.101947_b7","series-title":"Proc. International Conference on Machine Learning","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022"},{"key":"10.1016\/j.csl.2026.101947_b8","series-title":"Speech and Natural Language: Proceedings of a Workshop","first-page":"357","article-title":"The design for the wall street journal-based","author":"Douglas","year":"1992"},{"key":"10.1016\/j.csl.2026.101947_b9","unstructured":"Eeckt, S.V., et al., 2024. Unsupervised Online Continual Learning for Automatic Speech Recognition. In: Proc. INTERSPEECH."},{"key":"10.1016\/j.csl.2026.101947_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106230","article-title":"Source-free unsupervised domain adaptation: A survey","volume":"174","author":"Fang","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.csl.2026.101947_b11","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: A survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.csl.2026.101947_b12","article-title":"Semi-supervised learning by entropy minimization","volume":"vol. 17","author":"Grandvalet","year":"2004"},{"key":"10.1016\/j.csl.2026.101947_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.csl.2019.101056","article-title":"Low-resource text classification using domain-adversarial learning","volume":"62","author":"Grie\u00dfhaber","year":"2020","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.csl.2026.101947_b14","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.csl.2014.06.002","article-title":"Unsupervised language model adaptation using LDA-based mixture models and latent semantic marginals","volume":"29","author":"Haidar","year":"2015","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.csl.2026.101947_b15","first-page":"1491","article-title":"On Kullback-Leibler loss and density estimation","author":"Hall","year":"1987","journal-title":"Ann. Statist."},{"key":"10.1016\/j.csl.2026.101947_b16","series-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"10.1016\/j.csl.2026.101947_b17","first-page":"29566","article-title":"Self-taught recognizer: Toward unsupervised adaptation for speech foundation models","volume":"vol. 37","author":"Hu","year":"2024"},{"key":"10.1016\/j.csl.2026.101947_b18","series-title":"Proc. IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"7084","article-title":"Self-training for end-to-end speech recognition","author":"Kahn","year":"2020"},{"key":"10.1016\/j.csl.2026.101947_b19","series-title":"Proc. IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"6553","article-title":"Unsupervised domain adaptation for speech recognition via uncertainty driven self-training","author":"Khurana","year":"2021"},{"key":"10.1016\/j.csl.2026.101947_b20","series-title":"Proc. International Conference on Machine Learning","first-page":"11710","article-title":"Balancing discriminability and transferability for source-free domain adaptation","author":"Kundu","year":"2022"},{"key":"10.1016\/j.csl.2026.101947_b21","doi-asserted-by":"crossref","unstructured":"Kurmi, V.K., Subramanian, V.K., Namboodiri, V.P., 2021. Domain impression: A source data free domain adaptation method. In: Proc. Conference on Applications of Computer Vision. pp. 615\u2013625.","DOI":"10.1109\/WACV48630.2021.00066"},{"key":"10.1016\/j.csl.2026.101947_b22","first-page":"896","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume":"vol. 3","author":"Lee","year":"2013"},{"key":"10.1016\/j.csl.2026.101947_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.csl.2021.101226","article-title":"Unsupervised speech representation learning for behavior modeling using triplet enhanced contextualized networks","volume":"70","author":"Li","year":"2021","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.csl.2026.101947_b24","first-page":"635","article-title":"Shadow knowledge distillation: Bridging offline and online knowledge transfer","volume":"vol. 35","author":"Li","year":"2022"},{"key":"10.1016\/j.csl.2026.101947_b25","series-title":"Proc. International Conference on Machine Learning","first-page":"6028","article-title":"Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation","author":"Liang","year":"2020"},{"key":"10.1016\/j.csl.2026.101947_b26","doi-asserted-by":"crossref","unstructured":"Liang, J., Hu, D., Feng, J., He, R., 2022. Dine: Domain adaptation from single and multiple black-box predictors. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 8003\u20138013.","DOI":"10.1109\/CVPR52688.2022.00784"},{"key":"10.1016\/j.csl.2026.101947_b27","doi-asserted-by":"crossref","unstructured":"Likhomanenko, T., Xu, Q., Kahn, J., Synnaeve, G., Collobert, R., 2020. slimIPL: Language-model-free iterative pseudo-labeling. In: Proc. INTERSPEECH.","DOI":"10.21437\/Interspeech.2021-740"},{"key":"10.1016\/j.csl.2026.101947_b28","series-title":"Medical Imaging 2022: Image Processing, vol. 12032","first-page":"255","article-title":"Unsupervised domain adaptation for segmentation with black-box source model","author":"Liu","year":"2022"},{"key":"10.1016\/j.csl.2026.101947_b29","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/j.csl.2017.05.002","article-title":"Unsupervised crosslingual adaptation of tokenisers for spoken language recognition","volume":"46","author":"Ng","year":"2017","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.csl.2026.101947_b30","series-title":"Fairseq: A fast, extensible toolkit for sequence modeling","author":"Ott","year":"2019"},{"key":"10.1016\/j.csl.2026.101947_b31","series-title":"Proc. IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"7439","article-title":"Libri-adapt: A new speech dataset for unsupervised domain adaptation","author":"Panayotov","year":"2020"},{"key":"10.1016\/j.csl.2026.101947_b32","series-title":"Proc. IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"5206","article-title":"Librispeech: An asr corpus based on public domain audio books","author":"Panayotov","year":"2015"},{"key":"10.1016\/j.csl.2026.101947_b33","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al., 2020. Improved noisy student training for automatic speech recognition. In: Proc. INTERSPEECH.","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"10.1016\/j.csl.2026.101947_b34","doi-asserted-by":"crossref","unstructured":"Peng, Q., Ding, Z., Lyu, L., Sun, L., Chen, C., 2022a. RAIN: Regularization on input and network for black-box domain adaptation. In: Proc. International Joint Conference on Artificial Intelligence. IJCAI.","DOI":"10.24963\/ijcai.2023\/458"},{"key":"10.1016\/j.csl.2026.101947_b35","article-title":"Toward better target representation for source-free and black-box domain adaptation","author":"Peng","year":"2022","journal-title":"CoRR"},{"key":"10.1016\/j.csl.2026.101947_b36","series-title":"Proc. International Conference on Machine Learning","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023"},{"key":"10.1016\/j.csl.2026.101947_b37","doi-asserted-by":"crossref","unstructured":"Rousseau, A., Del\u00e9glise, P., Esteve, Y., 2012. TED-LIUM: An automatic speech recognition dedicated corpus. In: Proc. International Conference on Language Resources and Evaluation. LREC, pp. 125\u2013129.","DOI":"10.63317\/48xafxbrk3qa"},{"key":"10.1016\/j.csl.2026.101947_b38","first-page":"596","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume":"vol. 33","author":"Sohn","year":"2020"},{"key":"10.1016\/j.csl.2026.101947_b39","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"vol. 30","author":"Tarvainen","year":"2017"},{"key":"10.1016\/j.csl.2026.101947_b40","doi-asserted-by":"crossref","unstructured":"Wang, K., Liu, Y., Sheng, Q.Z., 2021. Neighborhood Intervention Consistency: Measuring Confidence for Knowledge Graph Link Prediction. In: IJCAI. pp. 2090\u20132096.","DOI":"10.24963\/ijcai.2021\/288"},{"key":"10.1016\/j.csl.2026.101947_b41","doi-asserted-by":"crossref","unstructured":"Watanabe, S., et al., 2018. ESPnet: End-to-end speech processing toolkit. In: Proc. INTERSPEECH.","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"10.1016\/j.csl.2026.101947_b42","series-title":"Huggingface\u2019s transformers: State-of-the-art natural language processing","author":"Wolf","year":"2019"},{"key":"10.1016\/j.csl.2026.101947_b43","first-page":"16005","article-title":"A separation and alignment framework for black-box domain adaptation","volume":"vol. 38","author":"Xia","year":"2024"},{"key":"10.1016\/j.csl.2026.101947_b44","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume":"vol. 33","author":"Xie","year":"2020"},{"key":"10.1016\/j.csl.2026.101947_b45","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M.-T., Hovy, E., Le, Q.V., 2020b. Self-training with noisy student improves imagenet classification. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 10687\u201310698.","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"10.1016\/j.csl.2026.101947_b46","series-title":"Leveraging endo-and exo-temporal regularization for black-box video domain adaptation","author":"Xu","year":"2022"},{"key":"10.1016\/j.csl.2026.101947_b47","doi-asserted-by":"crossref","first-page":"8934","DOI":"10.1109\/TKDE.2022.3220219","article-title":"A survey on deep semi-supervised learning","volume":"35","author":"Yang","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.csl.2026.101947_b48","series-title":"Proc. European Conference on Computer Vision","first-page":"299","article-title":"Mutualnet: Adaptive convnet via mutual learning from network width and resolution","author":"Yang","year":"2020"},{"key":"10.1016\/j.csl.2026.101947_b49","unstructured":"Yang, J., et al., 2022a. Divide to adapt: Mitigating confirmation bias for domain adaptation of black-box predictors. In: Proc. International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.csl.2026.101947_b50","doi-asserted-by":"crossref","DOI":"10.1016\/j.csl.2024.101641","article-title":"A closer look at reinforcement learning-based automatic speech recognition","volume":"87","author":"Yang","year":"2024","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.csl.2026.101947_b51","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1016\/j.csl.2009.03.004","article-title":"Active learning and semi-supervised learning for speech recognition: A unified framework using the global entropy reduction maximization criterion","volume":"24","author":"Yu","year":"2010","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.csl.2026.101947_b52","doi-asserted-by":"crossref","unstructured":"Zhang, J., Huang, J., Jiang, X., Lu, S., 2023. Black-box unsupervised domain adaptation with bi-directional atkinson-shiffrin memory. In: Proc. IEEE\/CVF International Conference on Computer Vision. ICCV, pp. 11771\u201311782.","DOI":"10.1109\/ICCV51070.2023.01081"},{"key":"10.1016\/j.csl.2026.101947_b53","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xiang, T., Hospedales, T.M., Lu, H., 2018. Deep mutual learning. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 4320\u20134328.","DOI":"10.1109\/CVPR.2018.00454"},{"key":"10.1016\/j.csl.2026.101947_b54","series-title":"Unsupervised domain adaptation of black-box source models","author":"Zhang","year":"2021"},{"key":"10.1016\/j.csl.2026.101947_b55","series-title":"Proc. IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Madi: Inter-domain matching and intra-domain discrimination for cross-domain speech recognition","author":"Zhou","year":"2023"}],"container-title":["Computer Speech & Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230826000100?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230826000100?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T21:13:49Z","timestamp":1779225229000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0885230826000100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":55,"alternative-id":["S0885230826000100"],"URL":"https:\/\/doi.org\/10.1016\/j.csl.2026.101947","relation":{},"ISSN":["0885-2308"],"issn-type":[{"value":"0885-2308","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Bumper-guided representation interpolation for black-box unsupervised domain adaptation","name":"articletitle","label":"Article Title"},{"value":"Computer Speech & Language","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.csl.2026.101947","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"101947"}}