{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T13:15:03Z","timestamp":1783602903600,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819533428","type":"print"},{"value":"9789819533435","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-3343-5_18","type":"book-chapter","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T06:30:27Z","timestamp":1763793027000},"page":"225-237","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Representation-Efficient Transfer Learning Approaches for\u00a0Speech Recognition and\u00a0Translation Using Pre-trained Speech Models"],"prefix":"10.1007","author":[{"given":"Wenhao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghe","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feilong","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,23]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Baby, A., Joseph, G., Singh, S.: Robust speaker personalisation using generalized low-rank adaptation for automatic speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 11381\u201311385 (2024)","DOI":"10.1109\/ICASSP48485.2024.10446630"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: Fleurs: few-shot learning evaluation of universal representations of speech. In: Spoken Language Technology Workshop (SLT), pp. 798\u2013805 (2023)","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics, pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Ghobrial, M.F., Gody, A.M., Muhammad, S.T.: Comparative study on end-to-end speech recognition using pre-trained models. Fayoum Univ. J. Eng. 8(1), 131\u2013142 (2025)","DOI":"10.21608\/fuje.2024.312102.1089"},{"key":"18_CR5","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, pp. 2790\u20132799 (2019)"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Hsu, W.-N., Bolte, B., Tsai, Y.-H.H., Lakhotia, K., Salakhutdinov, R., Mohamed, A.: Hubert: self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Trans. Audio, Speech Lang. Process. 29, 3451\u20133460 (2021)","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Kim, D., Lee, G., Shim, K., Shim, B.: Preserving pre-trained representation space: On effectiveness of prefix-tuning for large multi-modal models. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 797\u2013819 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.44"},{"key":"18_CR8","unstructured":"Kousha, P.: Designing Conversational AI Enabled Services and Performance Analysis Tools for High-Performance Computing. Ph.D thesis, The Ohio State University (2024)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Li, T., Wang, H., Li, Q., Ni, Z.: Vision-language relational transformer for video-to-text generation. IEEE Trans. Multimedia (2025)","DOI":"10.1109\/TMM.2025.3535394"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Li, X., Zhou, Y., Dou, Z.: UniGEN: a unified generative framework for retrieval and question answering with large language models. In: AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 8688\u20138696 (2024)","DOI":"10.1609\/aaai.v38i8.28714"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Li, Z., Mak, M.-W., Meng, M.-L.: Dual parameter-efficient fine-tuning for speaker representation via speaker prompt tuning and adapters. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 10751\u201310755 (2024)","DOI":"10.1109\/ICASSP48485.2024.10447795"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Lin, J., Yin, H., Ping,W., Molchanov, P., Shoeybi, M., Han, S.: Vila: on pre-training for visual language models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26689\u201326699 (2024)","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Liu, W., Qin, Y., Peng, Z., Lee, T.: Sparsely shared Lora on whisper for child speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 11751\u201311755 (2024)","DOI":"10.1109\/ICASSP48485.2024.10447004"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Luo, Y., et\u00a0al.: Fairclip: harnessing fairness in vision-language learning. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12289\u201312301 (2024)","DOI":"10.1109\/CVPR52733.2024.01168"},{"key":"18_CR15","unstructured":"Mazumder, M., et\u00a0al.: Multilingual spoken words corpus. In: Neural Information Processing Systems Datasets and Benchmarks Track (Round 2), pp. 1\u201317 (2021)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Popuri, S., et al.: Enhanced direct speech-to-speech translation using self-supervised pre-training and data augmentation. In: Interspeech 2022, pp. 5195\u20135199 (2022)","DOI":"10.21437\/Interspeech.2022-11032"},{"key":"18_CR17","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518 (2023)"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Sim, K.C., et al.: A comparison of parameter-efficient ASR domain adaptation methods for universal speech and language models. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6900\u20136904 (2024)","DOI":"10.1109\/ICASSP48485.2024.10445894"},{"key":"18_CR19","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.. Voxpopuli: a large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation. In: The 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 993\u20131003 (2021)","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Wu, Z., et al.: REFT: representation finetuning for language models. arXiv preprint arXiv:2404.03592 (2024)","DOI":"10.52202\/079017-2041"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Yusuf, B., Baskar, M.K., Rosenberg, A., Ramabhadran, B.: Speculative speech recognition by audio-prefixed low-rank adaptation of language models. In: Proceedings of the Interspeech 2024, pp. 792\u2013796 (2024)","DOI":"10.21437\/Interspeech.2024-298"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: Bridging modality gap with large speech and language models for end-to-end speech-to-text translation. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 (2025)","DOI":"10.1109\/ICASSP49660.2025.10890787"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3343-5_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T12:29:41Z","timestamp":1783600181000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3343-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,23]]},"ISBN":["9789819533428","9789819533435"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3343-5_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,23]]},"assertion":[{"value":"23 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}