{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T04:58:22Z","timestamp":1773637102396,"version":"3.50.1"},"reference-count":19,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,2,17]],"date-time":"2022-02-17T00:00:00Z","timestamp":1645056000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,17]],"date-time":"2022-02-17T00:00:00Z","timestamp":1645056000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. Pervasive Comp. Interact."],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s42486-022-00091-9","type":"journal-article","created":{"date-parts":[[2022,2,17]],"date-time":"2022-02-17T13:12:33Z","timestamp":1645103553000},"page":"158-171","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Human\u2013machine collaboration based sound event detection"],"prefix":"10.1007","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3648-8709","authenticated-orcid":false,"given":"Shengtong","family":"Ge","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwen","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,2,17]]},"reference":[{"issue":"6","key":"91_CR1","doi-asserted-by":"publisher","first-page":"162","DOI":"10.3390\/app6060162","volume":"6","author":"M Annamaria","year":"2016","unstructured":"Annamaria, M., Toni, H., Tuomas, V.: Metrics for polyphonic sound event detection. Appl. Sci. J. 6(6), 162 (2016)","journal-title":"Appl. Sci. J."},{"issue":"2","key":"91_CR2","first-page":"1","volume":"8","author":"K Bongjun","year":"2018","unstructured":"Bongjun, K., Bryan, P.: A Human-in-the-loop system for sound event detection and annotation. ACM Trans. Interact. Intell. Syst. J. 8(2), 1\u201313 (2018)","journal-title":"ACM Trans. Interact. Intell. Syst. J."},{"key":"91_CR3","doi-asserted-by":"crossref","unstructured":"Bongjun K, Shabnam G.: Self-supervised attention model for weakly labeled audio event classification. In: EUSIPCO, pp. 1\u20135 (2019)","DOI":"10.23919\/EUSIPCO.2019.8902567"},{"issue":"6","key":"91_CR4","first-page":"129l","volume":"25","author":"E Cakir","year":"2017","unstructured":"Cakir, E., Parascandolo, G., Heittola, T.: Convolutional recurrent neural networks for polyphonic sound event detection. IEEE\/ACM Trans. Audio Speech Lang. Process. J. 25(6), 129l\u20131303 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process. J."},{"key":"91_CR5","unstructured":"Gencoglu O, Virtanen H.: Recognition of acoustic events using deep neural networks. In: European Signal Processing Conference, pp. 5\u201310 (2014)"},{"key":"91_CR6","unstructured":"Heittola F, Mesaros A, Virtanen F.: Sound event detection in multisource environments using source separation. In: Machine Listening in Multisource Environments (2011)"},{"key":"91_CR7","doi-asserted-by":"crossref","unstructured":"Jort F, Gemmeke, Daniel P.W.E, Dylan F.: Audio set: an ontology and human-labeled dataset for audio events. In: ICASSP, pp. 776\u2013780 (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"91_CR8","doi-asserted-by":"crossref","unstructured":"Kong Q Q, Xu Y, Wang W W.: A joint detection-classification model for audio tagging of weakly labelled data. In : IEEE International Conference on Acoustics Speech and Signal Processing. New Orleans, LA, USA, pp.641\u2013645 (2017).","DOI":"10.1109\/ICASSP.2017.7952234"},{"issue":"5","key":"91_CR9","first-page":"644","volume":"13","author":"CC Lin","year":"2015","unstructured":"Lin, C.C., Chen, S.H., Truong, T.K.: Audio classification and categorization based on wavelets and support vector machine. IEEE Trans. Speech Audio Process. J. 13(5), 644\u2013651 (2015)","journal-title":"IEEE Trans. Speech Audio Process. J."},{"key":"91_CR10","doi-asserted-by":"crossref","unstructured":"Liwei L, Xiangdong W, Hong L, Yueliang Qian.: Guided learning for weakly-labeled semi-supervised sound event detection. In: ICASSP, pp. 626\u2013630 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053584"},{"key":"91_CR11","doi-asserted-by":"crossref","unstructured":"Lu R, Duan Z, Zhang C.: Multi-scale recurrent neural network for sound event detection. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 131\u2013135(2018)","DOI":"10.1109\/ICASSP.2018.8462006"},{"key":"91_CR12","unstructured":"Mesaros A, Heittola T, Eronen A.: Acoustic event detection in real life recordings. In: IEEE, pp. 1267\u20131271 (2010)"},{"key":"91_CR13","doi-asserted-by":"crossref","unstructured":"Parascandolo G, Huttunen H, VirtanenI T.: Recurrent neural networks for polyphonic sound event detection in real life recordings. In: ICASSP, pp. 6440\u20136444 (2016)","DOI":"10.1109\/ICASSP.2016.7472917"},{"key":"91_CR14","unstructured":"Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. Adv. Neural Inf. Process. Syst. NIPS\u00a03856\u20133866 (2017)"},{"key":"91_CR15","doi-asserted-by":"publisher","first-page":"2895","DOI":"10.1109\/TASLP.2020.3029652","volume":"28","author":"Z Shuyang","year":"2020","unstructured":"Shuyang, Z., Toni, H., Tuomas, V.: Active learning for sound event detection. IEEE ACM Trans. Audio Speech Lang. Process 28, 2895\u20132905 (2020)","journal-title":"IEEE ACM Trans. Audio Speech Lang. Process"},{"key":"91_CR16","unstructured":"Sidiropoulos E, Mezaris, Vkompatsiaris I.: On the use of audio events for improving video scene segmentation. In: International Workshop on Image Analysis for Multimedia Interactive Services WIAMlS.IEEE, pp. 1\u20134 (2010)"},{"key":"91_CR17","unstructured":"Tarvainen A, Valpola H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Neural Information Processing Systems, pp. 1196\u20131205 (2017)"},{"key":"91_CR18","unstructured":"Tery P K, Maddage N C, Kankanhalli M S.: Audio based event detection for multimedia surveillance. In: IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, vol. 5, pp.5\u20135 (2006)"},{"key":"91_CR19","doi-asserted-by":"crossref","unstructured":"Zhang H, McLoughlin I, Song Y.: Robust sound event recognition using convolutional neural works. In: ICASSP, pp. 559\u2013563 (2015)","DOI":"10.1109\/ICASSP.2015.7178031"}],"container-title":["CCF Transactions on Pervasive Computing and Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42486-022-00091-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42486-022-00091-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42486-022-00091-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T20:45:00Z","timestamp":1726692300000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42486-022-00091-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,17]]},"references-count":19,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["91"],"URL":"https:\/\/doi.org\/10.1007\/s42486-022-00091-9","relation":{},"ISSN":["2524-521X","2524-5228"],"issn-type":[{"value":"2524-521X","type":"print"},{"value":"2524-5228","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,17]]},"assertion":[{"value":"28 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 January 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}