{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T06:04:26Z","timestamp":1779516266081,"version":"3.53.1"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819509812","type":"print"},{"value":"9789819509829","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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\/978-981-95-0982-9_17","type":"book-chapter","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T22:25:12Z","timestamp":1759271112000},"page":"205-216","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Extending Pre-trained ASR Models to\u00a0Cross-Modal and\u00a0Cross-Lingual Speech-Text Retrieval"],"prefix":"10.1007","author":[{"given":"Yukai","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Si","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ju","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"issue":"2","key":"17_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3605943","volume":"56","author":"B Min","year":"2023","unstructured":"Min, B.: Recent advances in natural language processing via large pre-trained language models: a survey. ACM Comput. Surv. 56(2), 1\u201340 (2023)","journal-title":"ACM Comput. Surv."},{"issue":"8","key":"17_CR2","doi-asserted-by":"publisher","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","volume":"46","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 46(8), 5625\u20135644 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR3","unstructured":"Radford, A., Narasimhan, K.: \u201cImproving language understanding by generative pre-training,\u201d 2018"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: \u201cBERT: pre-training of deep bidirectional transformers for language understanding,\u201d In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp.\u00a04171\u20134186, 2019","DOI":"10.18653\/v1\/N19-1423"},{"key":"17_CR5","first-page":"13","volume":"32","author":"J Lu","year":"2019","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv. Neural. Inf. Process. Syst. 32, 13\u201323 (2019)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR6","unstructured":"A. Radford, et\u00a0al.: \u201cLearning transferable visual models from natural language supervision,\u201d In: Proceedings International conference on machine learning, pp.\u00a08748\u20138763, 2021"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Li, X., et\u00a0al.: \u201cOscar: object-semantics aligned pre-training for vision-language tasks,\u201d In: Proceedings European conference on computer vision, pp.\u00a0121\u2013137, 2020","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"17_CR8","first-page":"12449","volume":"33","author":"A Baevski","year":"2020","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: 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."},{"issue":"6","key":"17_CR9","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","volume":"16","author":"S Chen","year":"2022","unstructured":"Chen, S., et al.: Wavlm: large-scale self-supervised pre-training for full stack speech processing. IEEE J. Sel. Top. Sig. Proc. 16(6), 1505\u20131518 (2022)","journal-title":"IEEE J. Sel. Top. Sig. Proc."},{"key":"17_CR10","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"W-N Hsu","year":"2021","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. proc. 29, 3451\u20133460 (2021)","journal-title":"IEEE\/ACM trans. audio, speech, lang. proc."},{"key":"17_CR11","doi-asserted-by":"publisher","first-page":"2675","DOI":"10.1109\/TMM.2022.3149712","volume":"25","author":"AS Koepke","year":"2022","unstructured":"Koepke, A.S., Oncescu, A.-M., Henriques, J.F., Akata, Z., Albanie, S.: Audio retrieval with natural language queries: a benchmark study. IEEE Trans. Multimedia 25, 2675\u20132685 (2022)","journal-title":"IEEE Trans. Multimedia"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, K., Zhang, T., Hui, Y., Berg-Kirkpatrick, T., Dubnov, S.: \u201cLarge-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation,\u201d In: Procedings IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135, 2023","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"17_CR13","unstructured":"Duquenne, P.A., Schwenk, H., Sagot, B.: \u201cSentence-level multimodal and language-agnostic representations,\u201d arXiv:2308.11466, 2023"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Palma\u00a0Gomez, F., Sanabria, R., Sung, Y.-h., Cer, D., Dalmia, S., Hernandez\u00a0Abrego, G.: \u201cTransforming LLMs into cross-modal and cross-lingual retrieval systems,\u201d in Proc. IWSLT, pp.\u00a023\u201332, 2024","DOI":"10.18653\/v1\/2024.iwslt-1.4"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Kanda, N., Horiguchi, S., Takashima, R., Fujita, Y., Nagamatsu, K., Watanabe, S.: \u201cAuxiliary interference speaker loss for target-speaker speech recognition,\u201d In: Proceedings INTERSPEECH, pp.\u00a0236\u2013240, 2019","DOI":"10.21437\/Interspeech.2019-1126"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Puvvada, K.C., Lavrukhin, V., Ginsburg, B.: \u201cConformer-based target-speaker automatic speech recognition for single-channel audio,\u201d In: Proceedings International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135, 2023","DOI":"10.1109\/ICASSP49357.2023.10095115"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Z., Raj, D., Garc\u00eda, P., Khudanpur, S.: \u201cAdapting self-supervised models to multi-talker speech recognition using speaker embeddings,\u201d In: Proceedings IEEE international conference on acoustics, speech and signal processing (ICASSP), pp.\u00a01\u20135, 2023","DOI":"10.1109\/ICASSP49357.2023.10097139"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, W., Qian,Y.: \u201cWeakly-supervised speech pre-training: a case study on target speech recognition,\u201d In: Proceedings INTERSPEECH, pp.\u00a03517\u20133521, 2023","DOI":"10.21437\/Interspeech.2023-1280"},{"key":"17_CR19","unstructured":"Radford, A., Kim, J.W., Xu,T., Brockman, G., McLeavey, C., Sutskever, I.: \u201cRobust speech recognition via large-scale weak supervision,\u201d In: Proceedings International conference on machine learning, pp.\u00a028492\u201328518 (2023)"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"C.Li, Y., et al.: \u201cAdapting multi-lingual ASR models for handling multiple talkers,\u201d in Proc. INTERSPEECH, pp.\u00a01314\u20131318, 2023","DOI":"10.21437\/Interspeech.2023-1276"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Ma, H., Peng, Z., Shao, M., Li, J., Liu, J.: \u201cExtending whisper with prompt tuning to target-speaker asr,\u201d In: Proceedings IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a012516\u201312520, 2024","DOI":"10.1109\/ICASSP48485.2024.10447492"},{"key":"17_CR22","unstructured":"Hu, E.\u00a0J., et al.: \u201cLora: low-rank adaptation of large language models,\u201d In: Proceedings ICLR (2022)"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: \u201cFleurs: few-shot learning evaluation of universal representations of speech,\u201d In: IEEE Spoken Language Technology Workshop (SLT), pp.\u00a0798\u2013805 (2023)","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"adnd Anne\u00a0Wu, C.\u00a0W., Gu, J., Pino, J.: \u201cCovost 2 and massively multilingual speech translation,\u201d In: Proc. INTERSPEECH, pp.\u00a02247\u20132251, 2021","DOI":"10.21437\/Interspeech.2021-2027"},{"key":"17_CR25","unstructured":"Vaswani, A.: \u201cAttention is all you need,\u201d In: Proceedings Advances in neural information processing systems, pp.\u00a06000\u20136010, 2017"}],"container-title":["Lecture Notes in Computer Science","Advances in Swarm Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0982-9_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T05:05:35Z","timestamp":1779512735000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0982-9_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"ISBN":["9789819509812","9789819509829"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0982-9_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,1]]},"assertion":[{"value":"1 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICSI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Swarm Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Yokohama","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"11 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"swarm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iasei.org\/icsi2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}