{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T08:35:43Z","timestamp":1726043743945},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030304898"},{"type":"electronic","value":"9783030304904"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-30490-4_29","type":"book-chapter","created":{"date-parts":[[2019,9,8]],"date-time":"2019-09-08T23:02:47Z","timestamp":1567983767000},"page":"351-361","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust Sound Event Classification with Local Time-Frequency Information and Convolutional Neural Networks"],"prefix":"10.1007","author":[{"given":"Yanli","family":"Yao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,9,9]]},"reference":[{"issue":"4","key":"29_CR1","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1007\/978-1-4615-2281-2_11","volume":"2","author":"JB Allen","year":"1994","unstructured":"Allen, J.B.: How do humans process and recognize speech? IEEE Trans. Speech Audio Process. 2(4), 567\u2013577 (1994). https:\/\/doi.org\/10.1007\/978-1-4615-2281-2_11","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"3","key":"29_CR2","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1109\/TSA.2005.857575","volume":"14","author":"R Cai","year":"2006","unstructured":"Cai, R., Lu, L., Hanjalic, A., Zhang, H.J., Cai, L.H.: A flexible framework for key audio effects detection and auditory context inference. IEEE Trans. Audio Speech Lang. Process. 14(3), 1026\u20131039 (2006). https:\/\/doi.org\/10.1109\/TSA.2005.857575","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"9","key":"29_CR3","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1016\/j.patrec.2013.02.015","volume":"34","author":"J Dennis","year":"2013","unstructured":"Dennis, J., Tran, H.D., Chng, E.S.: Overlapping sound event recognition using local spectrogram features and the generalised hough transform. Pattern Recognit. Lett. 34(9), 1085\u20131093 (2013). https:\/\/doi.org\/10.1016\/j.patrec.2013.02.015","journal-title":"Pattern Recognit. Lett."},{"issue":"2","key":"29_CR4","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1109\/LSP.2010.2100380","volume":"18","author":"J Dennis","year":"2010","unstructured":"Dennis, J., Tran, H.D., Li, H.: Spectrogram image feature for sound event classification in mismatched conditions. IEEE Signal Process. Lett. 18(2), 130\u2013133 (2010). https:\/\/doi.org\/10.1109\/LSP.2010.2100380","journal-title":"IEEE Signal Process. Lett."},{"key":"29_CR5","doi-asserted-by":"publisher","unstructured":"Dennis, J., Yu, Q., Tang, H., Tran, H.D., Li, H.: Temporal coding of local spectrogram features for robust sound recognition. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 803\u2013807. IEEE (2013). https:\/\/doi.org\/10.1109\/ICASSP.2013.6637759","DOI":"10.1109\/ICASSP.2013.6637759"},{"issue":"3","key":"29_CR6","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1016\/j.sigpro.2011.10.001","volume":"92","author":"MV Ghiurcau","year":"2012","unstructured":"Ghiurcau, M.V., Rusu, C., Bilcu, R.C., Astola, J.: Audio based solutions for detecting intruders in wild areas. Signal Process. 92(3), 829\u2013840 (2012). https:\/\/doi.org\/10.1016\/j.sigpro.2011.10.001","journal-title":"Signal Process."},{"issue":"6","key":"29_CR7","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"Alex Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012). https:\/\/doi.org\/10.1145\/3065386","journal-title":"Communications of the ACM"},{"issue":"7553","key":"29_CR8","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015). https:\/\/doi.org\/10.1038\/nature14539","journal-title":"Nature"},{"key":"29_CR9","unstructured":"LeCun, Y., Bengio, Y., et al.: Convolutional networks for images, speech, and time series. In: The Handbook of Brain Theory and Neural Networks, vol. 3361, no. 10, p. 1995 (1995)"},{"issue":"11","key":"29_CR10","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"issue":"3","key":"29_CR11","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1109\/TASSP.1985.1164591","volume":"33","author":"Y Lee","year":"1985","unstructured":"Lee, Y., Kassam, S.: Generalized median filtering and related nonlinear filtering techniques. IEEE Trans. Acoust. Speech Signal Process 33(3), 672\u2013683 (1985)","journal-title":"IEEE Trans. Acoust. Speech Signal Process"},{"issue":"3","key":"29_CR12","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1109\/TASLP.2015.2389618","volume":"23","author":"I McLoughlin","year":"2015","unstructured":"McLoughlin, I., Zhang, H., Xie, Z., Song, Y., Xiao, W.: Robust sound event classification using deep neural networks. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(3), 540\u2013552 (2015). https:\/\/doi.org\/10.1109\/TASLP.2015.2389618","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"29_CR13","unstructured":"Nakamura, S., Hiyane, K., Asano, F., Nishiura, T., Yamada, T.: Acoustical sound database in real environments for sound scene understanding and hands-free speech recognition (2000)"},{"issue":"10","key":"29_CR14","doi-asserted-by":"publisher","first-page":"2965","DOI":"10.1016\/j.patcog.2008.05.008","volume":"41","author":"D O\u2019Shaughnessy","year":"2008","unstructured":"O\u2019Shaughnessy, D.: Automatic speech recognition: history, methods and challenges. Pattern Recognit. 41(10), 2965\u20132979 (2008)","journal-title":"Pattern Recognit."},{"key":"29_CR15","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1016\/j.neucom.2017.07.021","volume":"272","author":"I Ozer","year":"2018","unstructured":"Ozer, I., Ozer, Z., Findik, O.: Noise robust sound event classification with convolutional neural network. Neurocomputing 272, 505\u2013512 (2018). https:\/\/doi.org\/10.1016\/j.neucom.2017.07.021","journal-title":"Neurocomputing"},{"key":"29_CR16","doi-asserted-by":"publisher","unstructured":"Paliwal, K.K.: Spectral subband centroid features for speech recognition. In: Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998, (Cat. No. 98CH36181), vol. 2, pp. 617\u2013620. IEEE (1998). https:\/\/doi.org\/10.1109\/ICASSP.1998.675340","DOI":"10.1109\/ICASSP.1998.675340"},{"issue":"4","key":"29_CR17","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1109\/TASLP.2016.2530401","volume":"24","author":"H Phan","year":"2016","unstructured":"Phan, H., Hertel, L., Maass, M., Mazur, R., Mertins, A.: Learning representations for nonspeech audio events through their similarities to speech patterns. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(4), 807\u2013822 (2016). https:\/\/doi.org\/10.1109\/TASLP.2016.2530401","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"29_CR18","doi-asserted-by":"publisher","unstructured":"Piczak, K.J.: Environmental sound classification with convolutional neural networks. In: 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1\u20136. IEEE (2015). https:\/\/doi.org\/10.1109\/MLSP.2015.7324337","DOI":"10.1109\/MLSP.2015.7324337"},{"issue":"12","key":"29_CR19","doi-asserted-by":"publisher","first-page":"2605","DOI":"10.1109\/TIFS.2015.2469254","volume":"10","author":"RV Sharan","year":"2015","unstructured":"Sharan, R.V., Moir, T.J.: Subband time-frequency image texture features for robust audio surveillance. IEEE Trans. Inf. Forensics Secur. 10(12), 2605\u20132615 (2015). https:\/\/doi.org\/10.1109\/TIFS.2015.2469254","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"3","key":"29_CR20","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"Andrew Varga","year":"1993","unstructured":"Varga, A., Steeneken, H.J.: Assessment for automatic speech recognition: Ii. noisex-92: a database and an experiment to study the effect of additive noise on speech recognition systems. Speech Commun. 12(3), 247\u2013251 (1993). https:\/\/doi.org\/10.1016\/0167-6393(93)90095-3","journal-title":"Speech Communication"},{"key":"29_CR21","unstructured":"Walters, T.C.: Auditory-based processing of communication sounds. Ph.D. thesis, University of Cambridge (2011)"},{"key":"29_CR22","doi-asserted-by":"publisher","unstructured":"Wu, J., Chua, Y., Zhang, M., Li, H., Tan, K.C.: A spiking neural network framework for robust sound classification. Front. Neurosci. 12 (2018). https:\/\/doi.org\/10.3389\/fnins.2018.00836","DOI":"10.3389\/fnins.2018.00836"},{"key":"29_CR23","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.neucom.2018.06.022","volume":"313","author":"R Xiao","year":"2018","unstructured":"Xiao, R., Tang, H., Gu, P., Xu, X.: Spike-based encoding and learning of spectrum features for robust sound recognition. Neurocomputing 313, 65\u201373 (2018). https:\/\/doi.org\/10.1016\/j.neucom.2018.06.022","journal-title":"Neurocomputing"},{"issue":"6","key":"29_CR24","doi-asserted-by":"publisher","first-page":"2178","DOI":"10.1109\/TCYB.2018.2821692","volume":"49","author":"Q Yu","year":"2018","unstructured":"Yu, Q., Li, H., Tan, K.C.: Spike timing or rate? Neurons learn to make decisions for both through threshold-driven plasticity. IEEE Trans. Cybern. 49(6), 2178\u20132189 (2018). https:\/\/doi.org\/10.1109\/TCYB.2018.2821692","journal-title":"IEEE Trans. Cybern."},{"key":"29_CR25","doi-asserted-by":"publisher","unstructured":"Yu, Q., Yao, Y., Wang, L., Tang, H., Dang, J.: A multi-spike approach for robust sound recognition. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 890\u2013894. IEEE (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8682963","DOI":"10.1109\/ICASSP.2019.8682963"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Yu, Q., Yao, Y., Wang, L., Tang, H., Dang, J., Tan, K.C.: Robust environmental sound recognition with sparse key-point encoding and efficient multi-spike learning. arXiv preprint arXiv:1902.01094 (2019)","DOI":"10.1109\/TNNLS.2020.2978764"},{"key":"29_CR27","doi-asserted-by":"publisher","unstructured":"Zhang, H., McLoughlin, I., Song, Y.: Robust sound event recognition using convolutional neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 559\u2013563. IEEE (2015). https:\/\/doi.org\/10.1109\/ICASSP.2015.7178031","DOI":"10.1109\/ICASSP.2015.7178031"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Text and Time Series"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-30490-4_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,19]],"date-time":"2021-01-19T02:42:51Z","timestamp":1611024171000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-30490-4_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030304898","9783030304904"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-30490-4_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}