{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T05:53:26Z","timestamp":1763618006060,"version":"3.45.0"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031705656"},{"type":"electronic","value":"9783031705663"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70566-3_1","type":"book-chapter","created":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T18:29:51Z","timestamp":1725128991000},"page":"3-12","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Retrieval Augmented Spoken Language Generation for\u00a0Transport Domain"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6459-7630","authenticated-orcid":false,"given":"Gokul","family":"Srinivasagan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5542-149X","authenticated-orcid":false,"given":"Munir","family":"Georges","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,27]]},"reference":[{"key":"1_CR1","unstructured":"Abdullin, Y., Molla-Aliod, D., Ofoghi, B., Yearwood, J., Li, Q.: Synthetic dialogue dataset generation using LLM agents (2024). arXiv preprint arXiv:2401.17461"},{"key":"1_CR2","unstructured":"Asai, A., Wu, Z., Wang, Y., Sil, A., Hajishirzi, H.: Self-RAG: Learning to retrieve, generate, and critique through self-reflection (2023). arXiv preprint arXiv:2310.11511"},{"key":"1_CR3","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems, vol. 33, 12449\u201312460 (2020)"},{"key":"1_CR4","unstructured":"Barrault, L., et al.: SeamlessM4T-massively multilingual & multimodal machine translation (2023). arXiv preprint arXiv:2308.11596"},{"key":"1_CR5","unstructured":"Borgeaud, S., et\u00a0al.: Improving language models by retrieving from trillions of tokens. In: International Conference on Machine Learning, pp. 2206\u20132240. PMLR (2022)"},{"key":"1_CR6","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR7","doi-asserted-by":"publisher","unstructured":"Chiang, C.H., Lee, H.Y.: Can large language models be an alternative to human evaluations? In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 15607\u201315631. Association for Computational Linguistics, Toronto, Canada (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.870, https:\/\/aclanthology.org\/2023.acl-long.870","DOI":"10.18653\/v1\/2023.acl-long.870"},{"key":"1_CR8","unstructured":"Guu, K., Lee, K., Tung, Z., Pasupat, P., Chang, M.: Retrieval augmented language model pre-training. In: International Conference on Machine Learning, pp. 3929\u20133938. PMLR (2020)"},{"key":"1_CR9","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"WN 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. Process. 29, 3451\u20133460 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"1_CR10","unstructured":"Jiang, A.Q., et\u00a0al.: Mistral 7B (2023). arXiv preprint arXiv:2310.06825"},{"key":"1_CR11","unstructured":"Kandpal, N., Deng, H., Roberts, A., Wallace, E., Raffel, C.: Large language models struggle to learn long-tail knowledge. In: International Conference on Machine Learning, pp. 15696\u201315707. PMLR (2023)"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering (2020). arXiv preprint arXiv:2004.04906","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Labrak, Y., Bazoge, A., Morin, E., Gourraud, P.A., Rouvier, M., Dufour, R.: BioMistral: A collection of open-source pretrained large language models for medical domains (2024). arXiv preprint arXiv:2402.10373","DOI":"10.18653\/v1\/2024.findings-acl.348"},{"key":"1_CR14","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020)"},{"key":"1_CR15","unstructured":"Peng, R., Liu, K., Yang, P., Yuan, Z., Li, S.: Embedding-based retrieval with LLM for effective agriculture information extracting from unstructured data (2023). arXiv preprint arXiv:2308.03107"},{"key":"1_CR16","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. PMLR (2023)"},{"key":"1_CR17","unstructured":"Scao, T.L., et\u00a0al.: Bloom: A 176b-parameter open-access multilingual language model (2022). arXiv preprint arXiv:2211.05100"},{"key":"1_CR18","unstructured":"Sinitsin, A., Plokhotnyuk, V., Pyrkin, D., Popov, S., Babenko, A.: Editable neural networks (2020). arXiv preprint arXiv:2004.00345"},{"key":"1_CR19","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models (2023). arXiv preprint arXiv:2312.11805"},{"key":"1_CR20","unstructured":"Touvron, H., et\u00a0al.: Llama 2: Open foundation and fine-tuned chat models (2023). arXiv preprint arXiv:2307.09288"},{"key":"1_CR21","unstructured":"Tunstall, L., et\u00a0al.: Zephyr: Direct distillation of LM alignment (2023). arXiv preprint arXiv:2310.16944"},{"key":"1_CR22","unstructured":"Wang, X., et al.: KnowledGPT: Enhancing large language models with retrieval and storage access on knowledge bases (2023). arXiv preprint arXiv:2308.11761"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70566-3_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T05:14:40Z","timestamp":1763615680000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70566-3_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705656","9783031705663"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70566-3_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"27 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brno","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.tsdconference.org\/tsd2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}