{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T21:34:03Z","timestamp":1775079243310,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,25]]},"DOI":"10.1145\/3477314.3507106","type":"proceedings-article","created":{"date-parts":[[2022,5,7]],"date-time":"2022-05-07T00:37:36Z","timestamp":1651883856000},"page":"863-870","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Leveraging multimodal content for podcast summarization"],"prefix":"10.1145","author":[{"given":"Lorenzo","family":"Vaiani","sequence":"first","affiliation":[{"name":"Politecnico di Torino, Turin, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moreno","family":"La Quatra","sequence":"additional","affiliation":[{"name":"Politecnico di Torino, Turin, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Cagliero","sequence":"additional","affiliation":[{"name":"Politecnico di Torino, Turin, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paolo","family":"Garza","sequence":"additional","affiliation":[{"name":"Politecnico di Torino, Turin, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,5,6]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. Advances in Neural Information Processing Systems 33","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. Advances in Neural Information Processing Systems 33 (2020)."},{"key":"e_1_3_2_1_2_1","volume-title":"Variations of the similarity function of textrank for automated summarization. arXiv preprint arXiv:1602.03606","author":"Barrios Federico","year":"2016","unstructured":"Federico Barrios, Federico L\u00f3pez, Luis Argerich, and Rosa Wachenchauzer. 2016. Variations of the similarity function of textrank for automated summarization. arXiv preprint arXiv:1602.03606 (2016)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505652"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/SKG.2018.00033"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.519"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017197"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2003.1221239"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2267205"},{"key":"e_1_3_2_1_10_1","volume-title":"Exploring wav2vec 2.0 on speaker verification and language identification. CoRR abs\/2012.06185","author":"Fan Zhiyun","year":"2020","unstructured":"Zhiyun Fan, Meng Li, Shiyu Zhou, and Bo Xu. 2020. Exploring wav2vec 2.0 on speaker verification and language identification. CoRR abs\/2012.06185 (2020). arXiv:2012.06185 https:\/\/arxiv.org\/abs\/2012.06185"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.828699"},{"key":"e_1_3_2_1_12_1","unstructured":"Matthew Honnibal and Ines Montani. 2017. spaCy 2: Natural language understanding with Bloom embeddings convolutional neural networks and incremental parsing. (2017). To appear."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3402431"},{"key":"e_1_3_2_1_14_1","volume-title":"Jussi Karlgren, Aasish Pappu, Sravana Reddy, and Yongze Yu.","author":"Jones Rosie","year":"2021","unstructured":"Rosie Jones, Ben Carterette, Ann Clifton, Maria Eskevich, Gareth JF Jones, Jussi Karlgren, Aasish Pappu, Sravana Reddy, and Yongze Yu. 2021. Trec 2020 podcasts track overview. arXiv preprint arXiv:2103.15953 (2021)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.SP.1266.podcast-overview"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1114"},{"key":"e_1_3_2_1_17_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74--81. https:\/\/aclanthology.org\/W04-1013"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683758"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1387"},{"key":"e_1_3_2_1_20_1","volume-title":"Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations, ICLR 2019","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6--9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.470"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics","author":"Mihalcea Rada","year":"2004","unstructured":"Rada Mihalcea and Paul Tarau. 2004. TextRank: Bringing Order into Text. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Barcelona, Spain, 404--411. https:\/\/aclanthology.org\/W04-3252"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.99"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Rezvaneh Rezapour Sravana Reddy Ann Clifton and Rosie Jones. [n. d.]. Spotify at TREC 2020: Genre-Aware Abstractive Podcast Summarization. ([n. d.]).","DOI":"10.6028\/NIST.SP.1266.podcast-spotify2"},{"key":"e_1_3_2_1_26_1","volume-title":"Spotify at TREC 2020: Genre-Aware Abstractive Podcast Summarization. CoRR abs\/2104.03343","author":"Rezapour Rezvaneh","year":"2021","unstructured":"Rezvaneh Rezapour, Sravana Reddy, Ann Clifton, and Rosie Jones. 2021. Spotify at TREC 2020: Genre-Aware Abstractive Podcast Summarization. CoRR abs\/2104.03343 (2021). arXiv:2104.03343 https:\/\/arxiv.org\/abs\/2104.03343"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2809933"},{"key":"e_1_3_2_1_28_1","volume-title":"Automatic summarization of open-domain podcast episodes. arXiv preprint arXiv:2011.04132","author":"Song Kaiqiang","year":"2020","unstructured":"Kaiqiang Song, Chen Li, Xiaoyang Wang, Dong Yu, and Fei Liu. 2020. Automatic summarization of open-domain podcast episodes. arXiv preprint arXiv:2011.04132 (2020)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4507"},{"key":"e_1_3_2_1_30_1","volume-title":"Fine-tuning wav2vec2 for speaker recognition. arXiv preprint arXiv:2109.15053","author":"Vaessen Nik","year":"2021","unstructured":"Nik Vaessen and David A van Leeuwen. 2021. Fine-tuning wav2vec2 for speaker recognition. arXiv preprint arXiv:2109.15053 (2021)."},{"key":"e_1_3_2_1_31_1","volume-title":"PodSumm-Podcast Audio Summarization. arXiv preprint arXiv:2009.10315","author":"Vartakavi Aneesh","year":"2020","unstructured":"Aneesh Vartakavi and Amanmeet Garg. 2020. PodSumm-Podcast Audio Summarization. arXiv preprint arXiv:2009.10315 (2020)."},{"key":"e_1_3_2_1_32_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-677"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534082"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1499"},{"key":"e_1_3_2_1_37_1","volume-title":"Kunpeng Zhang, and Ling Fan.","author":"Zheng Chujie","year":"2020","unstructured":"Chujie Zheng, Harry Jiannan Wang, Kunpeng Zhang, and Ling Fan. 2020. A Baseline Analysis for Podcast Abstractive Summarization. arXiv preprint arXiv:2008.10648 (2020)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.552"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.19"}],"event":{"name":"SAC '22: The 37th ACM\/SIGAPP Symposium on Applied Computing","location":"Virtual Event","acronym":"SAC '22","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"]},"container-title":["Proceedings of the 37th ACM\/SIGAPP Symposium on Applied Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477314.3507106","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477314.3507106","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:28Z","timestamp":1750188688000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477314.3507106"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":39,"alternative-id":["10.1145\/3477314.3507106","10.1145\/3477314"],"URL":"https:\/\/doi.org\/10.1145\/3477314.3507106","relation":{},"subject":[],"published":{"date-parts":[[2022,4,25]]},"assertion":[{"value":"2022-05-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}