{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T18:10:09Z","timestamp":1774721409368,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819620531","type":"print"},{"value":"9789819620548","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\/978-981-96-2054-8_31","type":"book-chapter","created":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T15:48:00Z","timestamp":1735832880000},"page":"415-426","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Frequency-Aware Convolution for\u00a0Sound Event Detection"],"prefix":"10.1007","author":[{"given":"Tao","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,3]]},"reference":[{"key":"31_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2023.109411","volume":"210","author":"N Aryal","year":"2023","unstructured":"Aryal, N., Lee, S.W.: Frequency-based CNN and attention module for acoustic scene classification. Appl. Acoust. 210, 109411 (2023)","journal-title":"Appl. Acoust."},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Bilen, \u00c7., Ferroni, G., Tuveri, F., Azcarreta, J., Krstulovi\u0107, S.: A framework for the robust evaluation of sound event detection. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, pp. 61\u201365, April 2020","DOI":"10.1109\/ICASSP40776.2020.9052995"},{"key":"31_CR3","unstructured":"DCASE 2023 task 4: Task description. https:\/\/dcase.community\/challenge2023\/task-sound-event-detection-with-weak-labels-and-synthetic-soundscapes"},{"key":"31_CR4","unstructured":"Ebbers, J., Haeb-Umbach, R.: Self-trained audio tagging and sound event detection in domestic environments. In: Detection and Classification of Acoustic Scenes and Events (DCASE), pp. 226\u2014230 (2021)"},{"key":"31_CR5","doi-asserted-by":"publisher","unstructured":"Ebbers, J., Haeb-Umbach, R., Serizel, R.: Threshold independent evaluation of sound event detection scores. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1021\u20131025 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747556","DOI":"10.1109\/ICASSP43922.2022.9747556"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Guirguis, K., Schorn, C., Guntoro, A., Abdulatif, S., Yang, B.: SELD-TCN: sound event localization & detection via temporal convolutional networks. In: European Signal Processing Conference (EUSIPCO), Amsterdam, Netherlands, pp. 16\u201320, December 2021","DOI":"10.23919\/Eusipco47968.2020.9287716"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Koutini, K., Eghbalzadeh, H., Widmer, G.: Receptive-field-regularized CNN variants for acoustic scene classification. In: Workshop on Detection and Classification of Acoustic Scenes and Events, pp.\u00a01\u20135 (2019)","DOI":"10.33682\/cjd9-kc43"},{"key":"31_CR8","doi-asserted-by":"publisher","unstructured":"Li, K., Song, Y., Dai, L.R., McLoughlin, I., Fang, X., Liu, L.: AST-SED: an effective sound event detection method based on audio spectrogram transformer. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135 (2023). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10096853","DOI":"10.1109\/ICASSP49357.2023.10096853"},{"key":"31_CR9","doi-asserted-by":"publisher","unstructured":"Li, Y., Wang, X., Liu, H., Tao, R., Yan, L., Ouchi, K.: Semi-supervised sound event detection with local and global consistency regularization. In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 271\u2013275 (2024). https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10446386","DOI":"10.1109\/ICASSP48485.2024.10446386"},{"key":"31_CR10","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: International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, pp. 66\u201370, April 2020","DOI":"10.1109\/ICASSP40776.2020.9053609"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Nam, H., Kim, S., Ko, B., Park, Y.: Frequency dynamic convolution: frequency-adaptive pattern recognition for sound event detection. In: Interspeech, Incheon, Korea, pp. 2763\u20132767, September 2022","DOI":"10.21437\/Interspeech.2022-10127"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Nam, H., Kim, S.H., Park, Y.H.: FilterAugment: an acoustic environmental data augmentation method. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, Singapore, pp. 4308\u20134312, April 2022","DOI":"10.1109\/ICASSP43922.2022.9747680"},{"key":"31_CR13","unstructured":"Rakowski, A., Kosmider, M.: Frequency-aware CNN for open set acoustic scene classification. In: Proceedings of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019), New York, NY, pp. 25\u201326 (2019)"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Serizel, R., Turpault, N., Shah, A., Salamon, J.: Sound event detection in synthetic domestic environments. In: International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Spain, May 2020","DOI":"10.1109\/ICASSP40776.2020.9054478"},{"key":"31_CR15","doi-asserted-by":"publisher","unstructured":"Shao, N., Li, X., Li, X.: Fine-tune the pretrained ATST model for sound event detection. In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 911\u2013915 (2024). https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10446159","DOI":"10.1109\/ICASSP48485.2024.10446159"},{"key":"31_CR16","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Wakayama, K., Saito, S.: CNN-transformer with self-attention network for sound event detection. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 806\u2013810, Singapore, Singapore, April 2022","DOI":"10.1109\/ICASSP43922.2022.9747762"},{"key":"31_CR18","doi-asserted-by":"publisher","unstructured":"Xu, L., Wang, L., Bi, S., Liu, H., Wang, J.: Semi-supervised sound event detection with pre-trained model. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135 (2023). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10095687","DOI":"10.1109\/ICASSP49357.2023.10095687"},{"key":"31_CR19","unstructured":"Zhang, H., Ciss\u00e9, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (ICLR), Vancouver, Canada, April 2018"},{"issue":"6","key":"31_CR20","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1109\/TASLP.2017.2690575","volume":"25","author":"E \u00c7ak\u0131r","year":"2017","unstructured":"\u00c7ak\u0131r, E., Parascandolo, G., Heittola, T., Huttunen, H., Virtanen, T.: Convolutional recurrent neural networks for polyphonic sound event detection. IEEE\/ACM Trans. Audio Speech Lang. Process. 25(6), 1291\u20131303 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2054-8_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T01:42:03Z","timestamp":1742694123000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2054-8_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819620531","9789819620548"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2054-8_31","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":"3 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","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":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}