{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T10:34:38Z","timestamp":1762770878219,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819543946","type":"print"},{"value":"9789819543953","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"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\/978-981-95-4395-3_20","type":"book-chapter","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T10:29:56Z","timestamp":1762770596000},"page":"280-294","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimal Transport Regularization for\u00a0Speech Text Alignment in\u00a0Spoken Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2995-6270","authenticated-orcid":false,"given":"Wenze","family":"Xu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2290-910X","authenticated-orcid":false,"given":"Chun","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1282-3776","authenticated-orcid":false,"given":"Jiazhen","family":"Yu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0397-3935","authenticated-orcid":false,"given":"Sheng","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6408-5271","authenticated-orcid":false,"given":"Liang","family":"Gao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5952-6996","authenticated-orcid":false,"given":"Weihong","family":"Deng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"20_CR1","unstructured":"Arora, S., et\u00a0al.: On the landscape of spoken language models: a comprehensive survey. arXiv:2504.08528 (2025)"},{"key":"20_CR2","unstructured":"Chu, Y., et\u00a0al.: Qwen2-audio technical report. arXiv:2407.10759 (2024)"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Chuang, S.P., Sung, T.W., Liu, A.H., Lee, H.Y.: Worse WER, but better BLEU? Leveraging word embedding as intermediate in multitask end-to-end speech translation. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 5998\u20136003 (Jul 2020)","DOI":"10.18653\/v1\/2020.acl-main.533"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Conneau, A., et\u00a0al.: FLEURS: few-shot learning evaluation of universal representations of speech. In: 2022 IEEE Spoken Language Technology Workshop (SLT), pp. 798\u2013805 (2023)","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"20_CR5","unstructured":"Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, vol. 2, pp. 2292\u20132300. NIPS\u201913 (2013)"},{"key":"20_CR6","unstructured":"Dubey, A., et\u00a0al.: The llama 3 herd of models. arXiv:2407.21783 (2024)"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Fan, R., et\u00a0al.: AlignFormer: modality matching can achieve better zero-shot instruction-following speech-LLM. arXiv:2412.01145 (2024)","DOI":"10.1109\/JSTSP.2025.3588378"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Fathullah, Y., et\u00a0al.: AudioChatLlama: towards general-purpose speech abilities for LLMs. In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 5522\u20135532. Mexico City, Mexico (2024)","DOI":"10.18653\/v1\/2024.naacl-long.309"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Gaido, M., et\u00a0al.: CTC-based compression for direct speech translation. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 690\u2013696 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.57"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376. ICML \u201906 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"20_CR11","unstructured":"Ji, S., et\u00a0al.: WavChat: a survey of spoken dialogue models. arXiv:2411.13577 (2024)"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Kumar, S., et\u00a0al.: Performance evaluation of SLAM-ASR: the good, the bad, the ugly, and the way forward. In: 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), pp.\u00a01\u20135 (2025)","DOI":"10.1109\/ICASSPW65056.2025.11010998"},{"key":"20_CR13","unstructured":"Le, P.H., Gong, H., Wang, C., Pino, J., Lecouteux, B., Schwab, D.: Pre-training for speech translation: CTC meets optimal transport. In: Proceedings of the 40th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 18667\u201318685 (2023)"},{"key":"20_CR14","first-page":"24840","volume":"23","author":"Z Ma","year":"2025","unstructured":"Ma, Z., et al.: Speech recognition meets large language model: benchmarking, models, and exploration. Proc. AAAI Conf. Artif. Intell. 23, 24840\u201324848 (2025)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Ouyang, S., Ye, R., Li, L.: WACO: word-aligned contrastive learning for speech translation. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 3891\u20133907 (Jul 2023)","DOI":"10.18653\/v1\/2023.acl-long.216"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: LibriSpeech: an ASR corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206\u20135210 (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Pratap, V., Xu, Q., Sriram, A., Synnaeve, G., Collobert, R.: MLS: a large-scale multilingual dataset for speech research. In: Interspeech 2020, pp. 2757\u20132761 (2020)","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"20_CR18","unstructured":"Qwen Team: Qwen2.5: a party of foundation models (2024)"},{"key":"20_CR19","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., Mcleavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: Proceedings of the 40th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0202, pp. 28492\u201328518 (2023)"},{"key":"20_CR20","unstructured":"Tang, C., et\u00a0al.: SALMONN: towards generic hearing abilities for large language models. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"20_CR21","unstructured":"Torres, L.C., Pereira, L.M., Amini, M.H.: A survey on optimal transport for machine learning: theory and applications. arXiv:2106.01963 (2021)"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Tsiamas, I., G\u00e1llego, G.I., Fonollosa, J.A.R., Costa-juss\u00e0, M.R.: Pushing the limits of zero-shot end-to-end speech translation. In: Findings of the Association for Computational Linguistics: ACL 2024, pp. 14245\u201314267 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.847"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Wang, C., Wu, A., Pino, J.: CoVoST 2 and massively multilingual speech-to-text translation. arXiv:2007.10310 (2020)","DOI":"10.21437\/Interspeech.2021-2027"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Wu, J., et\u00a0al.: On decoder-only architecture for speech-to-text and large language model integration. In: 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp.\u00a01\u20138 (2023)","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Fang, Q., Feng, Y.: CMOT: cross-modal mixup via optimal transport for speech translation. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 7873\u20137887 (2023)","DOI":"10.18653\/v1\/2023.acl-long.436"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4395-3_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T10:30:01Z","timestamp":1762770601000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4395-3_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"ISBN":["9789819543946","9789819543953"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4395-3_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,11]]},"assertion":[{"value":"11 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gold Coast, QLD","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"10 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.acpr2025.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}