{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:06:41Z","timestamp":1776881201484,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T00:00:00Z","timestamp":1686528000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Slovenian Research Agency","award":["P2-0103"],"award-info":[{"award-number":["P2-0103"]}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/W001632\/1 and EP\/S033564\/1"],"award-info":[{"award-number":["EP\/W001632\/1 and EP\/S033564\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,12]]},"DOI":"10.1145\/3591106.3592270","type":"proceedings-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T22:33:38Z","timestamp":1686263618000},"page":"602-606","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Multimodal Topic Segmentation of Podcast Shows with Pre-trained Neural Encoders"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7409-7736","authenticated-orcid":false,"given":"Iacopo","family":"Ghinassi","sequence":"first","affiliation":[{"name":"School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8095-9518","authenticated-orcid":false,"given":"Lin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7235-9130","authenticated-orcid":false,"given":"Chris","family":"Newell","sequence":"additional","affiliation":[{"name":"R&D, BBC, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2297-1273","authenticated-orcid":false,"given":"Matthew","family":"Purver","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom and Institut Jo\u017eef Stefan, Slovenia"}]}],"member":"320","published-online":{"date-parts":[[2023,6,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-85251-1_1"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00261"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054315"},{"key":"e_1_3_2_1_4_1","volume-title":"Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit","author":"Bird Steven","unstructured":"Steven Bird and Ewan Klein. 2009. Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit. O\u2019Reilly Media Inc."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-329"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of CLUK 3.","author":"Choi F","year":"2000","unstructured":"F Choi. 2000. Linear text segmentation : approaches, advances and applications. In Proceedings of CLUK 3."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"e_1_3_2_1_8_1","volume-title":"NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference 1.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming\u00a0Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference 1."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-013-0350-0"},{"key":"e_1_3_2_1_10_1","volume-title":"Evaluating Text Segmentation. Master\u2019s thesis","author":"Fournier Chris","unstructured":"Chris Fournier. 2013. Evaluating Text Segmentation. Master\u2019s thesis. University of Ottawa."},{"key":"e_1_3_2_1_11_1","volume-title":"Proc. 51st Annual Meeting of the Association for Computational Linguistics. 1702\u20131712","author":"Fournier Chris","year":"2013","unstructured":"Chris Fournier. 2013. Evaluating Text Segmentation using Boundary Edit Distance. In Proc. 51st Annual Meeting of the Association for Computational Linguistics. 1702\u20131712."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION45008.2020.9190246"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075167"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.09.025"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5281\/ZENODO.4744399"},{"key":"e_1_3_2_1_16_1","volume-title":"TextTiling: Segmenting Text into Multi-paragraph Subtopic Passages. Computational Linguistics 23","author":"Hearst A.","year":"1997","unstructured":"Marti\u00a0A. Hearst. 1997. TextTiling: Segmenting Text into Multi-paragraph Subtopic Passages. Computational Linguistics 23 (1997). Issue 1."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_18_1","volume-title":"Proc. 3rd International Conference on Learning Representations (ICLR).","author":"P.","unstructured":"Diederik\u00a0P. Kingma and Jimmy\u00a0Lei Ba. 2015. Adam: A method for stochastic optimization. In Proc. 3rd International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2075"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1027527.1027678"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_22_1","volume-title":"RoBERTa: A robustly optimized BERT pretraining approach. arXiv","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A robustly optimized BERT pretraining approach. arXiv (2019)."},{"key":"e_1_3_2_1_23_1","unstructured":"Kelvin Lo Yuan Jin Weicong Tan Ming Liu Lan Du and Wray\u00a0L. Buntine. 2021. Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence. In EMNLP."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.380"},{"key":"e_1_3_2_1_25_1","volume-title":"The Kaldi Speech Recognition Toolkit. In IEEE 2011 Workshop on Automatic Speech Recognition and Understanding (Hilton Waikoloa Village","author":"Povey Daniel","year":"2011","unstructured":"Daniel Povey, Arnab Ghoshal, Gilles Boulianne, Lukas Burget, Ondrej Glembek, Nagendra Goel, Mirko Hannemann, Petr Motlicek, Yanmin Qian, Petr Schwarz, Jan Silovsky, Georg Stemmer, and Karel Vesely. 2011. The Kaldi Speech Recognition Toolkit. In IEEE 2011 Workshop on Automatic Speech Recognition and Understanding (Hilton Waikoloa Village, Big Island, Hawaii, US). IEEE Signal Processing Society. IEEE Catalog No.: CFP11SRW-USB."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781119992691.ch11"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268979"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"e_1_3_2_1_30_1","volume-title":"Unsupervised Topic Segmentation of Meetings with BERT Embeddings. arXiv","author":"Solbiati Alessandro","year":"2021","unstructured":"Alessandro Solbiati, Kevin Hefferman, Georgios Damaskinos, Shivani Poddar, Shubham Modi, and Jacques Cali. 2021. Unsupervised Topic Segmentation of Meetings with BERT Embeddings. arXiv (2021)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-392"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1162\/089120101300346796"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sigdial-1.18"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674435"}],"event":{"name":"ICMR '23: International Conference on Multimedia Retrieval","location":"Thessaloniki Greece","acronym":"ICMR '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2023 ACM International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592270","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3591106.3592270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:30Z","timestamp":1750178250000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592270"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,12]]},"references-count":34,"alternative-id":["10.1145\/3591106.3592270","10.1145\/3591106"],"URL":"https:\/\/doi.org\/10.1145\/3591106.3592270","relation":{},"subject":[],"published":{"date-parts":[[2023,6,12]]},"assertion":[{"value":"2023-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}