{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T22:40:10Z","timestamp":1751409610844,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819666010","type":"print"},{"value":"9789819665990","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-6599-0_15","type":"book-chapter","created":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T22:17:23Z","timestamp":1751408243000},"page":"214-227","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Highlight Detection in\u00a0Podcasts: A Multimodal Deep Learning Approach"],"prefix":"10.1007","author":[{"given":"Wongsapat","family":"Phuengpanyaloet","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nonpipat","family":"Boonruengkhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Viktor","family":"Anchutin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8359-9888","authenticated-orcid":false,"given":"Kitsuchart","family":"Pasupa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chu Kiong","family":"Loo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,2]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Altundogan, T.G., Karakose, M., Tanberk, S.: Transformer based multimodal summarization and highlight abstraction approach for texts and speech audios. In: Proceedings of the 28th International Conference on Information Technology, IT 2024, pp.\u00a01\u20134 (2024)","DOI":"10.1109\/IT61232.2024.10475775"},{"issue":"11","key":"15_CR2","doi-asserted-by":"publisher","first-page":"1838","DOI":"10.1109\/JPROC.2021.3117472","volume":"109","author":"E Apostolidis","year":"2021","unstructured":"Apostolidis, E., Adamantidou, E., Metsai, A.I., Mezaris, V., Patras, I.: Video summarization using deep neural networks: a survey. Proc. IEEE 109(11), 1838\u20131863 (2021)","journal-title":"Proc. IEEE"},{"issue":"5","key":"15_CR3","doi-asserted-by":"publisher","first-page":"1016","DOI":"10.1109\/TMM.2007.898890","volume":"9","author":"N Babaguchi","year":"2007","unstructured":"Babaguchi, N., Ohara, K., Ogura, T.: Learning personal preference from viewer\u2019s operations for browsing and its application to baseball video retrieval and summarization. IEEE Trans. Multimedia 9(5), 1016\u20131025 (2007)","journal-title":"IEEE Trans. Multimedia"},{"key":"15_CR4","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Proceedings of the Annual Conference on Neural Information Processing Systems, NeurIPS 2020, Virtual Event, 6\u201312 December 2020 (2020)"},{"issue":"2","key":"15_CR5","first-page":"236","volume":"14","author":"A Chester","year":"2011","unstructured":"Chester, A., Buntine, A., Hammond, K., Atkinson, L.: Podcasting in education: student attitudes, behaviour and self-efficacy. J. Educ. Technol. Soc. 14(2), 236\u2013247 (2011)","journal-title":"J. Educ. Technol. Soc."},{"key":"15_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of the 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, 3\u20137 May 2021. OpenReview.net (2021)"},{"key":"15_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105151","volume":"115","author":"MA Ganaie","year":"2022","unstructured":"Ganaie, M.A., Hu, M., Malik, A.K., Tanveer, M., Suganthan, P.N.: Ensemble deep learning: a review. Eng. Appl. Artif. Intell. 115, 105151 (2022)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Ghinassi, I., Wang, L., Newell, C., Purver, M.: Multimodal topic segmentation of podcast shows with pre-trained neural encoders. In: Proceedings of the 2023 ACM International Conference on Multimedia Retrieval, ICMR 2023, Thessaloniki, Greece, 12\u201315 June 2023, pp. 602\u2013606. ACM (2023)","DOI":"10.1145\/3591106.3592270"},{"key":"15_CR9","doi-asserted-by":"publisher","first-page":"3292","DOI":"10.1109\/TASLP.2021.3120633","volume":"29","author":"Y Gong","year":"2021","unstructured":"Gong, Y., Chung, Y., Glass, J.R.: PSLA: improving audio tagging with pretraining, sampling, labeling, and aggregation. IEEE ACM Trans. Audio Speech Lang. Process. 29, 3292\u20133306 (2021)","journal-title":"IEEE ACM Trans. Audio Speech Lang. Process."},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Hofst\u00e4tter, S., Sertkan, M., Hanbury, A.: TU Wien at TREC DL and podcast 2021: simple compression for dense retrieval. In: Proceedings of the Thirtieth Text REtrieval Conference, TREC 2021, online, 15\u201319 November 2021. NIST Special Publication, vol. 500-335. National Institute of Standards and Technology (NIST) (2021)","DOI":"10.6028\/NIST.SP.500-335.deep-TU_Vienna"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Jaimes, A., Echigo, T., Teraguchi, M., Satoh, F.: Learning personalized video highlights from detailed MPEG-7 metadata. In: Proceedings of the 2002 International Conference on Image Processing, ICIP 2002, Rochester, New York, USA, 22\u201325 September 2002, pp. 133\u2013136. IEEE (2002)","DOI":"10.1109\/ICIP.2002.1037977"},{"issue":"4","key":"15_CR12","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1109\/TAFFC.2017.2736999","volume":"10","author":"R Lotfian","year":"2019","unstructured":"Lotfian, R., Busso, C.: Building naturalistic emotionally balanced speech corpus by retrieving emotional speech from existing podcast recordings. IEEE Trans. Affect. Comput. 10(4), 471\u2013483 (2019)","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"4","key":"15_CR13","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1109\/TASLP.2019.2898816","volume":"27","author":"R Lotfian","year":"2019","unstructured":"Lotfian, R., Busso, C.: Curriculum learning for speech emotion recognition from crowdsourced labels. IEEE\/ACM Trans. Audio Speech Lang. Process. 27(4), 815\u2013826 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"4","key":"15_CR14","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1007\/s10489-014-0629-7","volume":"42","author":"K Noda","year":"2015","unstructured":"Noda, K., Yamaguchi, Y., Nakadai, K., Okuno, H.G., Ogata, T.: Audio-visual speech recognition using deep learning. Appl. Intell. 42(4), 722\u2013737 (2015)","journal-title":"Appl. Intell."},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Pasupa, K., Woraratpanya, K.: Enhancing Thai food recognition through multimodal fusion of image and fourier spectrum. In: Nguyen, N.T., et al. (eds.) Proceedings of the 16th Asian Conference on Intelligent Information and Database Systems (ACIIDS 2024), 15\u201318 April 2024, Ras Al Khaimah, UAE. Communications in Computer and Information Science, vol.\u00a02145, pp. 71\u201382. Springer (2024)","DOI":"10.1007\/978-981-97-5934-7_7"},{"issue":"3","key":"15_CR16","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1017\/S0954579405050340","volume":"17","author":"J Posner","year":"2005","unstructured":"Posner, J., Russell, J.A., Petersona, B.S.: The circumplex model of affect: An integrative approach to affective neuroscience, cognitive development, and psychopathology. Dev. Psychopathol. 17(3), 715\u2013734 (2005)","journal-title":"Dev. Psychopathol."},{"key":"15_CR17","unstructured":"PwC: IAB U.S. podcast advertising revenue study-FY2021. Technical report, PwC International Limited (2022). https:\/\/www.iab.com\/wp-content\/uploads\/2022\/05\/IAB-FY-2021-Podcast-Ad-Revenue-and-2022-2024-Growth-Projections_FINAL.pdf"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Roheda, S., Krim, H., Luo, Z., Wu, T.: Decision level fusion: an event driven approach. In: Proceedings of the 26th European Signal Processing Conference, EUSIPCO 2018, Roma, Italy, 3\u20137 September 2018, pp. 2598\u20132602. IEEE (2018)","DOI":"10.23919\/EUSIPCO.2018.8553412"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Song, K., Liu, F., Li, C., Wang, X., Yu, D.: Automatic summarization of open-domain podcast episodes. In: Proceedings of the Twenty-Ninth Text REtrieval Conference, TREC 2020, Virtual Event, 16\u201320 November 2020. NIST Special Publication, vol.\u00a01266. National Institute of Standards and Technology (NIST) (2020)","DOI":"10.6028\/NIST.SP.1266.podcast-UCF_NLP"},{"key":"15_CR20","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 10347\u201310357. PMLR (2021)"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Vaiani, L., Quatra, M.L., Cagliero, L., Garza, P.: Leveraging multimodal content for podcast summarization. In: Proceedings of the 37th ACM\/SIGAPP Symposium on Applied Computing, SAC 2022, Virtual Event, 25\u201329 April 2022, pp. 863\u2013870. ACM (2022)","DOI":"10.1145\/3477314.3507106"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Vanjari, N., Pinjari, S., Labde, S., Patil, P., Patil, P., Sahitya, A.: Podcast summarization system. In: Proceedings of the 5th International Conference on Advances in Science and Technology, ICAST 2022, pp. 379\u2013382 (2022)","DOI":"10.1109\/ICAST55766.2022.10039668"},{"key":"15_CR23","unstructured":"Vartakavi, A., Garg, A.: Podsumm\u2014podcast audio summarization. CoRR abs\/2009.10315 (2020)"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Vartakavi, A., Garg, A., Rafii, Z.: Audio summarization for podcasts. In: Proceedings of the 29th European Signal Processing Conference, EUSIPCO 2021, pp. 431\u2013435 (2021)","DOI":"10.23919\/EUSIPCO54536.2021.9615948"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Vielzeuf, V., Lechervy, A., Pateux, S., Jurie, F.: CentralNet: a multilayer approach for multimodal fusion. In: Proceedings of the European Conference on Computer Vision, ECCV 2018 Workshops, Munich, Germany, 8\u201314 September 2018. Lecture Notes in Computer Science, vol. 11134, pp. 575\u2013589. Springer (2018)","DOI":"10.1007\/978-3-030-11024-6_44"},{"issue":"9","key":"15_CR26","doi-asserted-by":"publisher","first-page":"10745","DOI":"10.1109\/TPAMI.2023.3263585","volume":"45","author":"J Wagner","year":"2023","unstructured":"Wagner, J., et al.: Dawn of the transformer era in speech emotion recognition: closing the valence gap. IEEE Trans. Pattern Anal. Mach. Intell. 45(9), 10745\u201310759 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1007\/978-3-030-58577-8_20","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Wu","year":"2020","unstructured":"Wu, P., et al.: Not only look, but also listen: learning multimodal violence detection under weak supervision. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 322\u2013339. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_20"},{"issue":"1","key":"15_CR28","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1080\/19479830903561035","volume":"1","author":"J Zhang","year":"2010","unstructured":"Zhang, J.: Multi-source remote sensing data fusion: status and trends. Int. J. Image Data Fusion 1(1), 5\u201324 (2010)","journal-title":"Int. J. Image Data Fusion"},{"issue":"8","key":"15_CR29","doi-asserted-by":"publisher","first-page":"5181","DOI":"10.1109\/TNNLS.2021.3119969","volume":"34","author":"B Zhao","year":"2023","unstructured":"Zhao, B., Gong, M., Li, X.: Audiovisual video summarization. IEEE Trans. Neural Netw. Learn. Syst. 34(8), 5181\u20135188 (2023)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6599-0_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T22:17:27Z","timestamp":1751408247000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6599-0_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819666010","9789819665990"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6599-0_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"2 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}