{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T09:57:16Z","timestamp":1774605436046,"version":"3.50.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T00:00:00Z","timestamp":1757376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T00:00:00Z","timestamp":1757376000000},"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":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s00034-025-03314-3","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T10:34:09Z","timestamp":1757414049000},"page":"2090-2108","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Rare Sound Event Detection Using Multi-resolution Cochleagram Features and CRNN with Attention Mechanism"],"prefix":"10.1007","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6209-0281","authenticated-orcid":false,"given":"Garima","family":"Pandey","sequence":"first","affiliation":[]},{"given":"Shashidhar G.","family":"Koolagudi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,9]]},"reference":[{"key":"3314_CR1","unstructured":"S. Amiriparian, N. Cummins, S. Julka et al., Deep convolutional recurrent neural network for rare acoustic event detection, in 44th German Annual Conference on Acoustics (2018), pp. 1522\u20131525"},{"issue":"3","key":"3314_CR2","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/MSP.2014.2326181","volume":"32","author":"D Barchiesi","year":"2015","unstructured":"D. Barchiesi, D. Giannoulis, D. Stowell et al., Acoustic scene classification: classifying environments from the sounds they produce. IEEE Signal Process. Mag. 32(3), 16\u201334 (2015)","journal-title":"IEEE Signal Process. Mag."},{"key":"3314_CR3","volume-title":"Auditory Scene Analysis: The Perceptual Organization of Sound","author":"AS Bregman","year":"1994","unstructured":"A.S. Bregman, Auditory Scene Analysis: The Perceptual Organization of Sound (MIT Press, Cambridge, 1994)"},{"key":"3314_CR4","unstructured":"E. Cak\u0131r, T. Virtanen, Convolutional recurrent neural networks for rare sound event detection, in Proceedings of the Detection and Classification of Acoustic Scenes and Events 2017 Workshop (2019), pp. 27\u201331"},{"key":"3314_CR5","doi-asserted-by":"crossref","unstructured":"E. Cakir, T. Heittola, H. Huttunen et al., Polyphonic sound event detection using multi label deep neural networks, in IEEE International Joint Conference on Neural Networks (IJCNN) (2015), pp. 1\u20137","DOI":"10.1109\/IJCNN.2015.7280624"},{"issue":"6","key":"3314_CR6","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1109\/TASLP.2017.2690575","volume":"25","author":"E Cakir","year":"2017","unstructured":"E. Cakir, G. Parascandolo, T. Heittola et al., 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."},{"issue":"9","key":"3314_CR7","doi-asserted-by":"publisher","first-page":"963","DOI":"10.1109\/TBME.2002.802012","volume":"49","author":"K Chan","year":"2002","unstructured":"K. Chan, T.W. Lee, P. Sample et al., Comparison of machine learning and traditional classifiers in glaucoma diagnosis. IEEE Trans. Biomed. Eng. 49(9), 963\u2013974 (2002)","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"3314_CR8","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1016\/j.procs.2020.03.209","volume":"167","author":"H Chaurasiya","year":"2020","unstructured":"H. Chaurasiya, Time-frequency representations: spectrogram, cochleogram and correlogram. Proc. Comput. Sci. 167, 1901\u20131910 (2020)","journal-title":"Proc. Comput. Sci."},{"issue":"6","key":"3314_CR9","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.1109\/TSMC.2013.2244211","volume":"43","author":"B Chen","year":"2013","unstructured":"B. Chen, C. Chen, J. Wang, Smart homecare surveillance system: behavior identification based on state-transition support vector machines and sound directivity pattern analysis. IEEE Trans. Syst. Man Cyber. Syst. 43(6), 1279\u20131289 (2013)","journal-title":"IEEE Trans. Syst. Man Cyber. Syst."},{"issue":"1","key":"3314_CR10","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/TITS.2015.2470216","volume":"17","author":"P Foggia","year":"2015","unstructured":"P. Foggia, N. Petkov, A. Saggese et al., Audio surveillance of roads: a system for detecting anomalous sounds. IEEE Trans. Intell. Transp. Syst. 17(1), 279\u2013288 (2015)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"1","key":"3314_CR11","first-page":"6340","volume":"18","author":"M Freitag","year":"2017","unstructured":"M. Freitag, S. Amiriparian, S. Pugachevskiy et al., Unsupervised learning of representations from audio with deep recurrent neural networks. J. Mach. Learn. Res. 18(1), 6340\u20136344 (2017)","journal-title":"J. Mach. Learn. Res."},{"key":"3314_CR12","unstructured":"D. Giannoulis, D. Stowell, E. Benetos et al., A database and challenge for acoustic scene classification and event detection, in 21st European Signal Processing Conference (EUSIPCO) (2013), pp. 1\u20135"},{"key":"3314_CR13","doi-asserted-by":"crossref","unstructured":"L. He, D. Jiang, L. Yang et al., Multimodal affective dimension prediction using deep bidirectional long short-term memory recurrent neural networks, in Proceedings of the 5th International Workshop on Audio\/Visual Emotion Challenge (2015), pp. 73\u201380","DOI":"10.1145\/2808196.2811641"},{"key":"3314_CR14","doi-asserted-by":"crossref","unstructured":"C.C. Kao, W. Wang, M. Sun et al., R-CRNN: region-based convolutional recurrent neural network for audio event detection, in Proceedings of Interspeech (2018), pp. 1358\u20131362","DOI":"10.21437\/Interspeech.2018-2323"},{"key":"3314_CR15","unstructured":"H. Lim, J. Park, Y. Han, Rare sound event detection using 1D convolutional recurrent neural networks, in Detection and Classification of Acoustic Scenes and Events (DCASE) (2017), pp. 80\u201384"},{"issue":"6","key":"3314_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/app6060162","volume":"6","author":"A Mesaros","year":"2016","unstructured":"A. Mesaros, T. Heittola, T. Virtanen, Metrics for polyphonic sound event detection. Appl. Sci. 6(6), 1\u201317 (2016)","journal-title":"Appl. Sci."},{"key":"3314_CR17","unstructured":"A. Mesaros, T. Heittola, A. Diment et al., DCASE 2017 challenge setup: tasks, datasets and baseline system, in Proceedings of the Detection and Classification of Acoustic Scenes and Events 2017 Workshop (2017), pp. 85\u201392"},{"issue":"6","key":"3314_CR18","doi-asserted-by":"publisher","first-page":"992","DOI":"10.1109\/TASLP.2019.2907016","volume":"27","author":"A Mesaros","year":"2019","unstructured":"A. Mesaros, A. Diment, B. Elizalde et al., Sound event detection in the DCASE 2017 challenge. IEEE\/ACM Trans. Audio Speech Lang. Process. 27(6), 992\u20131006 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"10","key":"3314_CR19","doi-asserted-by":"publisher","first-page":"3473","DOI":"10.1002\/acs.3885","volume":"38","author":"Z Peng","year":"2024","unstructured":"Z. Peng, X. Song, S. Song et al., Spatiotemporal fault estimation for switched nonlinear reaction\u2013diffusion systems via adaptive iterative learning. Int. J. Adapt. Control Signal Process. 38(10), 3473\u20133483 (2024)","journal-title":"Int. J. Adapt. Control Signal Process."},{"key":"3314_CR20","doi-asserted-by":"crossref","unstructured":"H. Phan, M. Krawczyk-Becker, T. Gerkmann et al., Weighted and multi-task loss for rare audio event detection, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2018), pp. 336\u2013340","DOI":"10.1109\/ICASSP.2018.8461353"},{"key":"3314_CR21","unstructured":"M. Rajapakse, L. Wyse, Generic audio classification using a hybrid model based on GMMs and HMMs, in 11th IEEE International Multimedia Modelling Conference (2005), pp. 53\u201358"},{"issue":"3","key":"3314_CR22","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/LSP.2017.2657381","volume":"24","author":"J Salamon","year":"2017","unstructured":"J. Salamon, J.P. Bello, Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process. Lett. 24(3), 279\u2013283 (2017)","journal-title":"IEEE Signal Process. Lett."},{"issue":"12","key":"3314_CR23","doi-asserted-by":"publisher","first-page":"2605","DOI":"10.1109\/TIFS.2015.2469254","volume":"10","author":"RV Sharan","year":"2015","unstructured":"R.V. Sharan, T.J. Moir, Subband time-frequency image texture features for robust audio surveillance. IEEE Trans. Inf. Forensics Secur. 10(12), 2605\u20132615 (2015)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"3314_CR24","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.1109\/TMM.2015.2428998","volume":"10","author":"D Stowell","year":"2015","unstructured":"D. Stowell, D. Giannoulis, E. Benetos et al., Detection and classification of acoustic scenes and events. IEEE Trans. Multimed. 10, 1733\u20131746 (2015)","journal-title":"IEEE Trans. Multimed."},{"key":"3314_CR25","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1016\/j.isatra.2024.12.023","volume":"157","author":"Y Sun","year":"2025","unstructured":"Y. Sun, H. Tao, V. Stojanovic, End-to-end multi-scale residual network with parallel attention mechanism for fault diagnosis under noise and small samples. ISA Trans. 157, 419\u2013433 (2025)","journal-title":"ISA Trans."},{"key":"3314_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2024.102986","volume":"64","author":"Y Sun","year":"2025","unstructured":"Y. Sun, H. Tao, V. Stojanovic, Pseudo-label guided dual classifier domain adversarial network for unsupervised cross-domain fault diagnosis with small samples. Adv. Eng. Inform. 64, 102986 (2025)","journal-title":"Adv. Eng. Inform."},{"key":"3314_CR27","doi-asserted-by":"crossref","unstructured":"N. Surampudi, M. Srirangan, J. Christopher, Enhanced feature extraction approaches for detection of sound events, in IEEE 9th International Conference on Advanced Computing (IACC) (2019), pp. 223\u2013229","DOI":"10.1109\/IACC48062.2019.8971574"},{"issue":"4","key":"3314_CR28","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1016\/j.patcog.2005.11.005","volume":"39","author":"A Temko","year":"2006","unstructured":"A. Temko, C. Nadeu, Classification of acoustic events using SVM-based clustering schemes. Pattern Recogn. 39(4), 682\u2013694 (2006)","journal-title":"Pattern Recogn."},{"key":"3314_CR29","unstructured":"X. Valero, F. Al\u00edas, Gammatone wavelet features for sound classification in surveillance applications, in Proceedings of the 20th European Signal Processing Conference (EUSIPCO) (2012), pp. 1658\u20131662"},{"key":"3314_CR30","unstructured":"L. Vuegen, B. Broeck, P. Karsmakers et al., An MFCC-GMM approach for event detection and classification, in IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) (2013), pp. 1\u20133"},{"key":"3314_CR31","doi-asserted-by":"crossref","unstructured":"J. Wang, S. Li, Comparing the influence of depth and width of deep neural network based on fixed number of parameters for audio event detection, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2018), pp. 2681\u20132685","DOI":"10.1109\/ICASSP.2018.8461713"},{"key":"3314_CR32","unstructured":"K. Wang, L. Yang, B. Yang, Audio event detection and classification using extended R-FCN approach, in Proceedings of the Detection and Classification of Acoustic Scenes and Events 2017 Workshop (2017), pp. 128\u2013132"},{"key":"3314_CR33","doi-asserted-by":"crossref","unstructured":"X. Zhuang, X. Zhou, T.S. Huang et al., Feature analysis and selection for acoustic event detection, in IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2008), pp. 17\u201320","DOI":"10.1109\/ICASSP.2008.4517535"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-025-03314-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-025-03314-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-025-03314-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T09:14:10Z","timestamp":1774602850000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-025-03314-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,9]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["3314"],"URL":"https:\/\/doi.org\/10.1007\/s00034-025-03314-3","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,9]]},"assertion":[{"value":"29 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 August 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}]}}