{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T04:01:18Z","timestamp":1749355278721,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819665754","type":"print"},{"value":"9789819665761","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\/978-981-96-6576-1_5","type":"book-chapter","created":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T05:38:15Z","timestamp":1749274695000},"page":"58-72","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Critical Feature Sifting and\u00a0Dynamic Aggregation for\u00a0Anomalous Audio Sequence Detection"],"prefix":"10.1007","author":[{"given":"Erteng","family":"Liu","sequence":"first","affiliation":[]},{"given":"Kewei","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Xing","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Sen","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Jianhai","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yijun","family":"Bei","sequence":"additional","affiliation":[]},{"given":"Zunlei","family":"Feng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,8]]},"reference":[{"key":"5_CR1","unstructured":"Dufaux, A., Besacier, L., Ansorge, M., Pellandini, F.: Automatic sound detection and recognition for noisy environment. In: 2000 10th European Signal Processing Conference, pp.\u00a01\u20134. IEEE (2000)"},{"key":"5_CR2","doi-asserted-by":"publisher","first-page":"200","DOI":"10.4028\/www.scientific.net\/AMR.601.200","volume":"601","author":"BD Barkana","year":"2012","unstructured":"Barkana, B.D., Uzkent, B., Saricicek, I.: Normal and abnormal non-speech audio event detection using MFCC and PR-based feature sets. Adv. Mater. Res. 601, 200\u2013208 (2012)","journal-title":"Adv. Mater. Res."},{"issue":"1","key":"5_CR3","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12564","volume":"38","author":"B Bayram","year":"2021","unstructured":"Bayram, B., Duman, T.B., Ince, G.: Real time detection of acoustic anomalies in industrial processes using sequential autoencoders. Expert. Syst. 38(1), e12564 (2021)","journal-title":"Expert. Syst."},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Becker, P., Roth, C., Roennau, A., Dillmann, R.: Acoustic anomaly detection in additive manufacturing with long short-term memory neural networks. In: 2020 IEEE 7th International Conference on Industrial Engineering and Applications (ICIEA), pp. 921\u2013926. IEEE (2020)","DOI":"10.1109\/ICIEA49774.2020.9102002"},{"key":"5_CR5","unstructured":"Beckmann, P., Kegler, M., Saltini, H., Cernak, M.: Speech-VGG: a deep feature extractor for speech processing. arXiv preprint arXiv:1910.09909 (2019)"},{"key":"5_CR6","unstructured":"Chan, C.F., Yu, E.W.M.: An abnormal sound detection and classification system for surveillance applications. In: 2010 18th European Signal Processing Conference, pp. 1851\u20131855 (2010)"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Yang, Y., Wang, W., Hu, W., Zhuang, Y., Song, G.: Time2graph: revisiting time series modeling with dynamic shapelets. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 3617\u20133624 (2020)","DOI":"10.1609\/aaai.v34i04.5769"},{"issue":"2","key":"5_CR8","doi-asserted-by":"publisher","first-page":"205","DOI":"10.20965\/jaciii.2017.p0205","volume":"21","author":"CP Dadula","year":"2017","unstructured":"Dadula, C.P., Dadios, E.P.: Fuzzy logic system for abnormal audio event detection using MEL frequency cepstral coefficients. J. Adv. Comput. Intell. Intell. Inform. 21(2), 205\u2013210 (2017)","journal-title":"J. Adv. Comput. Intell. Intell. Inform."},{"issue":"8","key":"5_CR9","doi-asserted-by":"publisher","first-page":"2009","DOI":"10.1016\/j.sigpro.2005.09.027","volume":"86","author":"M Davy","year":"2006","unstructured":"Davy, M., Desobry, F., Gretton, A., Doncarli, C.: An online support vector machine for abnormal events detection. Signal Process. 86(8), 2009\u20132025 (2006)","journal-title":"Signal Process."},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Desplanques, B., Thienpondt, J., Demuynck, K.: ECAPA-TDNN: emphasized channel attention, propagation and aggregation in TDNN based speaker verification. arXiv preprint arXiv:2005.07143 (2020)","DOI":"10.21437\/Interspeech.2020-2650"},{"issue":"1","key":"5_CR11","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/TITS.2015.2470216","volume":"17","author":"P Foggia","year":"2016","unstructured":"Foggia, P., Petkov, N., Saggese, A., Strisciuglio, N., Vento, M.: Audio surveillance of roads: a system for detecting anomalous sounds. IEEE Trans. Intell. Transp. Syst. 17(1), 279\u2013288 (2016). https:\/\/doi.org\/10.1109\/TITS.2015.2470216","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"2","key":"5_CR12","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","volume":"43","author":"SH Gao","year":"2019","unstructured":"Gao, S.H., Cheng, M.M., Zhao, K., Zhang, X.Y., Yang, M.H., Torr, P.: Res2net: a new multi-scale backbone architecture. IEEE Trans. Pattern Anal. Mach. Intell. 43(2), 652\u2013662 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Graves, A., Graves, A.: Long short-term memory. In: Supervised Sequence Labelling with Recurrent Neural Networks, pp. 37\u201345 (2012)","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"5_CR14","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"5_CR15","doi-asserted-by":"publisher","first-page":"2880","DOI":"10.1109\/TASLP.2020.3030497","volume":"28","author":"Q Kong","year":"2020","unstructured":"Kong, Q., Cao, Y., Iqbal, T., Wang, Y., Wang, W., Plumbley, M.D.: PANNs: large-scale pretrained audio neural networks for audio pattern recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 2880\u20132894 (2020)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"5_CR16","volume":"364","author":"R Lang","year":"2020","unstructured":"Lang, R., Lu, R., Zhao, C., Qin, H., Liu, G.: Graph-based semi-supervised one class support vector machine for detecting abnormal lung sounds. Appl. Math. Comput. 364, 124487 (2020)","journal-title":"Appl. Math. Comput."},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Lecomte, S., Lengelle, R., Richard, C., Capman, F.: One class support vector machines for audio abnormal events detection. In: Statistical Signal Processing Workshop (2011)","DOI":"10.1109\/SSP.2011.5967739"},{"issue":"6","key":"5_CR18","first-page":"117","volume":"11","author":"XL Li","year":"2005","unstructured":"Li, X.L., Du, Z.L., Wang, T., Yu, D.M.: Audio feature selection based on rough set. Int. J. Inf. Technol. 11(6), 117\u2013123 (2005)","journal-title":"Int. J. Inf. Technol."},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, B., Zhao, R., Yao, W., Shen, M., Yang, J.: A novel method for broiler abnormal sound detection using WMFCC and HMM. J. Sensors 2020 (2020)","DOI":"10.1155\/2020\/2985478"},{"issue":"1","key":"5_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12559-020-09773-x","volume":"13","author":"M Mahmud","year":"2021","unstructured":"Mahmud, M., Kaiser, M.S., McGinnity, T.M., Hussain, A.: Deep learning in mining biological data. Cogn. Comput. 13(1), 1\u201333 (2021)","journal-title":"Cogn. Comput."},{"key":"5_CR21","doi-asserted-by":"publisher","first-page":"2063","DOI":"10.1109\/TNNLS.2018.2790388","volume":"29","author":"M Mahmud","year":"2018","unstructured":"Mahmud, M., Kaiser, M.S., Hussain, A., Vassanelli, S.: Applications of deep learning and reinforcement learning to biological data. IEEE Trans. Neural Netw. Learn. Syst. 29, 2063\u20132079 (2018)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"5_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/978-3-642-21735-7_7","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2011","author":"J Masci","year":"2011","unstructured":"Masci, J., Meier, U., Cire\u015fan, D., Schmidhuber, J.: Stacked convolutional auto-encoders for hierarchical feature extraction. In: Honkela, T., Duch, W., Girolami, M., Kaski, S. (eds.) ICANN 2011. LNCS, vol. 6791, pp. 52\u201359. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-21735-7_7"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Megha, C.K., Reddy, V.K.: Robust classification of abnormal audio using background-foreground separation. In: IEEE India Council International Conference (2017)","DOI":"10.1109\/INDICON.2017.8487922"},{"key":"5_CR24","doi-asserted-by":"publisher","first-page":"51142","DOI":"10.1109\/ACCESS.2022.3174124","volume":"10","author":"S Mekruksavanich","year":"2022","unstructured":"Mekruksavanich, S., Jitpattanakul, A., Sitthithakerngkiet, K., Youplao, P., Yupapin, P.: Resnet-se: Channel attention-based deep residual network for complex activity recognition using wrist-worn wearable sensors. IEEE Access 10, 51142\u201351154 (2022)","journal-title":"IEEE Access"},{"issue":"10","key":"5_CR25","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.3390\/electronics9101593","volume":"9","author":"I Papadimitriou","year":"2020","unstructured":"Papadimitriou, I., Vafeiadis, A., Lalas, A., Votis, K., Tzovaras, D.: Audio-based event detection at different snr settings using two-dimensional spectrogram magnitude representations. Electronics 9(10), 1593 (2020)","journal-title":"Electronics"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Purohit, H., et al.: MIMII dataset: sound dataset for malfunctioning industrial machine investigation and inspection. arXiv preprint arXiv:1909.09347 (2019)","DOI":"10.33682\/m76f-d618"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Sufisher2017anomaly, Y., Zhang, K., Wang, J., Madani, K.: Environment sound classification using a two-stream CNN based on decision-level fusion. Sensors 19(7), 1733 (2019)","DOI":"10.3390\/s19071733"},{"issue":"3","key":"5_CR29","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/29.21701","volume":"37","author":"A Waibel","year":"1989","unstructured":"Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., Lang, K.J.: Phoneme recognition using time-delay neural networks. IEEE Trans. Acoust. Speech Signal Process. 37(3), 328\u2013339 (1989)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"5_CR30","unstructured":"Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent neural network regularization. arXiv preprint arXiv:1409.2329 (2014)"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Zeng, W., Lin, Z., Yuan, C., Wang, Q., Wang, Y.: A new learning and classification framework for the detection of abnormal heart sound signals using hybrid signal processing and neural networks. In: 2020 39th Chinese Control Conference (CCC) (2020)","DOI":"10.23919\/CCC50068.2020.9189522"},{"issue":"1","key":"5_CR32","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1051\/jnwpu\/20203810162","volume":"38","author":"K Zhang","year":"2020","unstructured":"Zhang, K., Su, Y., Wang, J., Wang, S., Zhang, Y.: Environment sound classification system based on hybrid feature and convolutional neural network. Xibei Gongye Daxue Xuebao\/J. Northwest. Polytech. Univ. 38(1), 162\u2013169 (2020)","journal-title":"Xibei Gongye Daxue Xuebao\/J. Northwest. Polytech. Univ."}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6576-1_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T05:38:23Z","timestamp":1749274703000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6576-1_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819665754","9789819665761"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6576-1_5","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":"8 June 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"}}]}}