{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T04:03:16Z","timestamp":1745640196458,"version":"3.40.4"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T00:00:00Z","timestamp":1745539200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T00:00:00Z","timestamp":1745539200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62171470"],"award-info":[{"award-number":["No.62171470"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Henan Zhongyuan Science and Technology Innovation Leading Talent Project","award":["No.234200510019"],"award-info":[{"award-number":["No.234200510019"]}]},{"DOI":"10.13039\/501100004761","name":"Natural Science Foundation of Henan Province of China","doi-asserted-by":"crossref","award":["No.232300421240"],"award-info":[{"award-number":["No.232300421240"]}],"id":[{"id":"10.13039\/501100004761","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"DOI":"10.1186\/s13636-025-00406-5","type":"journal-article","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T08:17:27Z","timestamp":1745569047000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Parameter-efficient adaptation with multi-channel adversarial training for far-field speech recognition"],"prefix":"10.1186","volume":"2025","author":[{"given":"Tong","family":"Niu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaqi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9917-7794","authenticated-orcid":false,"given":"Dan","family":"Qu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hengbo","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"ChengRan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"issue":"2","key":"406_CR1","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1109\/JPROC.2020.3018668","volume":"109","author":"R Haeb-Umbach","year":"2020","unstructured":"R. Haeb-Umbach, J. Heymann, L. Drude, S. Watanabe, M. Delcroix, T. Nakatani, Far-field automatic speech recognition. Proc. IEEE 109(2), 124\u2013148 (2020)","journal-title":"Proc. IEEE"},{"key":"406_CR2","first-page":"12449","volume":"33","author":"A Baevski","year":"2020","unstructured":"A. Baevski, Y. Zhou, A. Mohamed, M. Auli, wav2vec 2.0: A framework for self-supervised learning of speech representations. Adv. Neural Inf. Process. Syst. 33, 12449\u201312460 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"406_CR3","unstructured":"A. Radford, J.W. Kim, T. Xu, G. Brockman, C. McLeavey, I. Sutskever, in International conference on machine learning. Robust speech recognition via large-scale weak supervision (PMLR,\u00a0New York, 2023), pp. 28492\u201328518"},{"key":"406_CR4","unstructured":"V. Pratap, A. Tjandra, B. Shi, P. Tomasello, A. Babu, S. Kundu, A.M. Elkahky, Z. Ni, A. Vyas, M. Fazel-Zarandi, A. Baevski, Y. Adi, X. Zhang, W.N. Hsu, A. Conneau, M. Auli, Scaling speech technology to 1, 000+ languages.\u00a0J. Mach. Learn. Res.\u00a025,\u00a097:1-97:52 (2024).\u00a0https:\/\/jmlr.org\/papers\/v25\/23-1318.html"},{"key":"406_CR5","unstructured":"N. Houlsby, A. Giurgiu, S. Jastrzebski, B. Morrone, Q. De Laroussilhe, A. Gesmundo, M. Attariyan, S. Gelly, in International conference on machine learning. Parameter-efficient transfer learning for nlp (PMLR, New York, 2019), pp. 2790\u20132799"},{"key":"406_CR6","doi-asserted-by":"crossref","unstructured":"B. Thomas, S. Kessler, S. Karout, in ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Efficient adapter transfer of self-supervised speech models for automatic speech recognition (IEEE,\u00a0Piscataway, 2022), pp. 7102\u20137106","DOI":"10.1109\/ICASSP43922.2022.9746223"},{"key":"406_CR7","unstructured":"E.J. Hu, Y. Shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, W. Chen, Lora: Low-rank adaptation of large language models. The Tenth International Conference on Learning Representations, [ICLR] 2022, Virtual Event, April 25-29, 2022 (OpenReview.net, 2022).\u00a0https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"406_CR8","unstructured":"C.H.H. Yang, Y.Y. Tsai, P.Y. Chen, in International conference on machine learning. Voice2series: Reprogramming acoustic models for time series classification (PMLR, 2021),\u00a0Stroudsburg. pp. 11808\u201311819"},{"key":"406_CR9","doi-asserted-by":"crossref","unstructured":"K.W. Chang, M.H. Chen, Y.P. Lin, J.N. Hsu, P.K.M. Huang, C. Yu\u00a0Huang, S.W. Li, H. Yi\u00a0Lee, in 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Prompting and adapter tuning for self-supervised encoder-decoder speech model (IEEE,\u00a0Piscataway, 2023), pp. 1\u20138","DOI":"10.1109\/ASRU57964.2023.10389731"},{"key":"406_CR10","doi-asserted-by":"publisher","unstructured":"P. Peng, B. Yan, S. Watanabe, D.F. Harwath, Prompting the hidden talent of web-scale speech models for zero-shot task generalization. 24th Annual Conference of the International Speech Communication Association, Interspeech 2023, Dublin, Ireland, August 20-24, 2023,\u00a0396-400 (ISCA, 2023). https:\/\/doi.org\/10.21437\/INTERSPEECH.2023-2032","DOI":"10.21437\/INTERSPEECH.2023-2032"},{"key":"406_CR11","doi-asserted-by":"crossref","unstructured":"X. Liu, K. Ji, Y. Fu, W.L. Tam, Z. Du, Z. Yang, J. Tang, in Annual Meeting of the Association for Computational Linguistics. P-tuning: Prompt tuning can be comparable to fine-tuning across scales and tasks (Association for Computational Linguistics (ACL),\u00a0Stroudsburg, PA, 2022)","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"406_CR12","doi-asserted-by":"crossref","unstructured":"F.T. Liao, Y.C. Chan, Y.C. Chen, C.J. Hsu, D. Shan\u00a0Shiu, in 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Zero-shot domain-sensitive speech recognition with prompt-conditioning fine-tuning (IEEE,\u00a0Piscataway, 2023), pp. 1\u20138","DOI":"10.1109\/ASRU57964.2023.10389617"},{"issue":"59","key":"406_CR13","first-page":"1","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Y. Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. March, V. Lempitsky, Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(59), 1\u201335 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"406_CR14","doi-asserted-by":"crossref","unstructured":"E. Tzeng, J. Hoffman, K. Saenko, T. Darrell, in Proceedings of the IEEE conference on computer vision and pattern recognition. Adversarial discriminative domain adaptation (IEEE,\u00a0Piscataway, 2017), pp. 7167\u20137176","DOI":"10.1109\/CVPR.2017.316"},{"key":"406_CR15","doi-asserted-by":"crossref","unstructured":"Y. Shinohara, in Interspeech. Adversarial multi-task learning of deep neural networks for robust speech recognition (ISCA, San Francisco, 2016), pp. 2369\u20132372","DOI":"10.21437\/Interspeech.2016-879"},{"key":"406_CR16","doi-asserted-by":"publisher","unstructured":"R. Ma, M. Qian, M.J.F. Gales, K. Knill,\u00a0ed. by H.\u00a0Strik, R.\u00a0Divekar and C.\u00a0Cucchiarini. Adapting an (ASR) foundation model for spoken language assessment. 9th Workshop on Speech and Language Technology in Education, SLaTE 2023, Dublin, Ireland, August 18-20, 2023, p. 104-108 (ISCA, 2023).\u00a0https:\/\/doi.org\/10.21437\/SLaTE.2023-20","DOI":"10.21437\/SLaTE.2023-20"},{"key":"406_CR17","doi-asserted-by":"publisher","unstructured":"H. Ma, Z. Peng, M. Shao, J. Li, J. Liu, Extending whisper with prompt tuning to target-speaker (ASR). (IEEE) International Conference on Acoustics, Speech and Signal Processing,(ICASSP) 2024, Seoul, Republic of Korea, April 14-19, 2024 (IEEE, 2024), p.\u00a012516-12520.\u00a0https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10447492","DOI":"10.1109\/ICASSP48485.2024.10447492"},{"key":"406_CR18","unstructured":"X.L. Li, P. Liang, in Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Prefix-tuning: Optimizing continuous prompts for generation (2021), pp. 4582\u20134597"},{"key":"406_CR19","doi-asserted-by":"crossref","unstructured":"B. Lester, R. Al-Rfou, N. Constant, in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. The power of scale for parameter-efficient prompt tuning (Association for Computational Linguistics,\u00a0Stroudsburg, 2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"406_CR20","doi-asserted-by":"publisher","unstructured":"M. Van Segbroeck, A. Zaid, K. Kutsenko, C. Huerta, T. Nguyen, X. Luo, B. Hoffmeister, J. Trmal, M. Omologo, R. Maas. ed. by H. Meng, B. Xu and T. F. Zheng. Dipco\u2013dinner party corpus. 21st Annual Conference of the International Speech Communication Association, Interspeech 2020, Virtual Event, Shanghai, China, October 25-29, 2020 (ISCA, 2020), p.\u00a0434-436.\u00a0https:\/\/doi.org\/10.21437\/Interspeech.2020-2800","DOI":"10.21437\/Interspeech.2020-2800"},{"key":"406_CR21","doi-asserted-by":"crossref","unstructured":"S. Watanabe, M. Mandel, J. Barker, E. Vincent, A. Arora, X. Chang, S. Khudanpur, V. Manohar, D. Povey, D. Raj, et al., in 6th International Workshop on Speech Processing in Everyday Environments (CHiME 2020). Chime-6 challenge: Tackling multispeaker speech recognition for unsegmented recordings (ISCA,\u00a0Grenoble, 2020)","DOI":"10.21437\/CHiME.2020-1"},{"key":"406_CR22","unstructured":"L. Drude, J. Heymann, C. Boeddeker, R. Haeb-Umbach, in Speech Communication; 13th ITG-Symposium. Nara-wpe: A python package for weighted prediction error dereverberation in numpy and tensorflow for online and offline processing (VDE,\u00a0Heidelberg, 2018), pp. 1\u20135"},{"issue":"7","key":"406_CR23","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1109\/TASL.2007.902460","volume":"15","author":"X Anguera","year":"2007","unstructured":"X. Anguera, C. Wooters, J. Hernando, Acoustic beamforming for speaker diarization of meetings. IEEE Trans. Audio Speech Lang. Process. 15(7), 2011\u20132022 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"406_CR24","doi-asserted-by":"crossref","unstructured":"C. Boeddeker, J. Heitkaemper, J. Schmalenstroeer, L. Drude, J. Heymann, R. Haeb-Umbach, in Proc. CHiME 2018 Workshop on Speech Processing in Everyday Environments, Hyderabad, India. Front-end processing for the chime-5 dinner party scenario (ISCA,\u00a0Grenoble, 2018)","DOI":"10.21437\/CHiME.2018-8"},{"key":"406_CR25","doi-asserted-by":"publisher","unstructured":"S. Cornell, M. Wiesner, S. Watanabe, D. Raj, X. Chang, P. Garc\u00eda, Y. Masuyama, Z.Q. Wang, S. Squartini, S. Khudanpur, The chime-7 (DASR) challenge: Distant meeting transcription with multiple devices in diverse scenarios.\u00a0CoRR,\u00a0abs\/2306.13734\u00a0(2023).\u00a0https:\/\/doi.org\/10.48550\/arXiv.2306.13734","DOI":"10.48550\/arXiv.2306.13734"},{"key":"406_CR26","doi-asserted-by":"crossref","unstructured":"S. Watanabe, T. Hori, S. Karita, T. Hayashi, J. Nishitoba, Y. Unno, N.E.Y. Soplin, J. Heymann, M. Wiesner, N. Chen, et al., Espnet: End-to-end speech processing toolkit.\u00a0CoRR.\u00a0abs\/1804.00015\u00a0(2018).\u00a0http:\/\/arxiv.org\/abs\/1804.00015","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"406_CR27","doi-asserted-by":"publisher","unstructured":"S. Cornell, T. Park, S. Huang, C. B\u00f6ddeker, X. Chang, M. Maciejewski, M. Wiesner, P. Garc\u00eda, S. Watanabe, The chime-8 DASR challenge for generalizable and array agnostic distant automatic speech recognition and diarization.\u00a0(2024).\u00a0CoRR\u00a0abs\/2407.16447. https:\/\/doi.org\/10.48550\/ARXIV.2407.16447","DOI":"10.48550\/ARXIV.2407.16447"}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-025-00406-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13636-025-00406-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-025-00406-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T08:17:42Z","timestamp":1745569062000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-025-00406-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,25]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["406"],"URL":"https:\/\/doi.org\/10.1186\/s13636-025-00406-5","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,25]]},"assertion":[{"value":"17 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors approve and consent to participate.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors consent for publication.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"19"}}