{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T21:39:51Z","timestamp":1757540391608,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781919"},{"type":"electronic","value":"9783031781926"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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\/978-3-031-78192-6_7","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T11:20:18Z","timestamp":1733224818000},"page":"98-113","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Generating Pseudo-Strong Labels from\u00a0Weak Labels for\u00a0Distributed Multi-Microphone Sound Event Detection"],"prefix":"10.1007","author":[{"given":"Vijay","family":"John","sequence":"first","affiliation":[]},{"given":"Yasutomo","family":"Kawanishi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Adavanne, S., Politis, A., Virtanen, T.: Multichannel sound event detection using 3d convolutional neural networks for learning inter-channel features. arXiv\/1801.09522 (2018)","DOI":"10.1109\/IJCNN.2018.8489542"},{"key":"7_CR2","unstructured":"Boes, W., Van\u00a0hamme, H.: Impact of temporal resolution on convolutional recurrent networks for audio tagging and sound event detection. In: Proceedings of the 7th Detection and Classification of Acoustic Scenes and Events 2022 Workshop (DCASE2022), pp.\u00a01\u20135 (2022)"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Casebeer, J., Wang, Z., Smaragdis, P.: Multi-view networks for multi-channel audio classification. In: Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 940\u2013944 (2019)","DOI":"10.1109\/ICASSP.2019.8682947"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Dang, A., Vu, T.H., Wang, J.C.: Acoustic scene classification using convolutional neural networks and multi-scale multi-feature extraction. In: Proceedings of the IEEE International Conference on Consumer Electronics, pp.\u00a01\u20134 (2018)","DOI":"10.1109\/ICCE.2018.8326315"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Deshmukh, S., Raj, B., Singh, R.: Improving weakly supervised sound event detection with self-supervised auxiliary tasks. arXiv\/2106.06858 (2021)","DOI":"10.21437\/Interspeech.2021-2079"},{"issue":"6","key":"7_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/app10062198","volume":"10","author":"X Fan","year":"2020","unstructured":"Fan, X., Jiang, W., Luo, H., Mao, W., Yu, H.: Instance hard triplet loss for in-video person re-identification. Appl. Sci. 10(6), 1\u201318 (2020)","journal-title":"Appl. Sci."},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Gong, Y., Chung, Y.A., Glass, J.: AST: audio spectrogram transformer. In: Proceedings of the INTERSPEECH Conference, pp. 571\u2013575 (2021)","DOI":"10.21437\/Interspeech.2021-698"},{"key":"7_CR8","unstructured":"John, V., Kawanishi, Y.: Multi-view video-based learning: leveraging weak labels for frame-level perception. arXiv\/2403.11616 (2024)"},{"key":"7_CR9","doi-asserted-by":"publisher","first-page":"2450","DOI":"10.1109\/TASLP.2020.3014737","volume":"28","author":"Q Kong","year":"2020","unstructured":"Kong, Q., Xu, Y., Wang, W., Plumbley, M.D.: Sound event detection of weakly labelled data with CNN-transformer and automatic threshold optimization. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 2450\u20132460 (2020)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Mei, P., Yang, J., Zhang, Q., Huang, X.: A method of sound event localization and detection based on three-dimension convolution. In: Proceedings of the 7th International Conference on Image, Vision and Computing, pp. 872\u2013878 (2022)","DOI":"10.1109\/ICIVC55077.2022.9886722"},{"issue":"5","key":"7_CR11","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/MSP.2021.3090678","volume":"38","author":"A Mesaros","year":"2021","unstructured":"Mesaros, A., Heittola, T., Virtanen, T., Plumbley, M.D.: Sound event detection: a tutorial. IEEE Signal Process. Mag. 38(5), 67\u201383 (2021)","journal-title":"IEEE Signal Process. Mag."},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Miyazaki, K., Komatsu, T., Hayashi, T., Watanabe, S., Toda, T., Takeda, K.: Weakly-supervised sound event detection with self-attention. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 66\u201370 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053609"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Park, C., Kim, D., Ko, H.: Sound event detection by pseudo-labeling in weakly labeled dataset. Sensors 21(24) (2021)","DOI":"10.3390\/s21248375"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Phan, H., et al.: Multi-view audio and music classification. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 611\u2013615 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414551"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Tseng, S., Li, J., Wang, Y., Szurley, J., Metze, F., Das, S.: Multiple instance deep learning for weakly supervised audio event detection. arXiv\/1712.09673 (2017)","DOI":"10.21437\/Interspeech.2018-1120"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Yasuda, M., Ohishi, Y., Saito, S., Harado, N.: Multi-view and multi-modal event detection utilizing transformer-based multi-sensor fusion. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4638\u20134642 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746006"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78192-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T12:15:21Z","timestamp":1733228121000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78192-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031781919","9783031781926"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78192-6_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 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":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}