{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T18:41:44Z","timestamp":1726080104674},"publisher-location":"Berlin, Heidelberg","reference-count":22,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783662615096"},{"type":"electronic","value":"9783662615102"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-662-61510-2_7","type":"book-chapter","created":{"date-parts":[[2020,4,11]],"date-time":"2020-04-11T06:02:25Z","timestamp":1586584945000},"page":"70-82","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Detecting Aging Substation Transformers by Audio Signal with Deep Neural Network"],"prefix":"10.1007","author":[{"given":"Wei","family":"Ye","sequence":"first","affiliation":[]},{"given":"Jiasai","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Min","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Xuemeng","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Hongliang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,4,12]]},"reference":[{"issue":"2","key":"7_CR1","doi-asserted-by":"publisher","first-page":"2157","DOI":"10.1016\/j.eswa.2011.07.065","volume":"39","author":"OC Ai","year":"2012","unstructured":"Ai, O.C., Hariharan, M., Yaacob, S., Chee, L.S.: Classification of speech dysfluencies with MFCC and LPCC features. Exp. Syst. Appl. 39(2), 2157\u20132165 (2012)","journal-title":"Exp. Syst. Appl."},{"issue":"11","key":"7_CR2","doi-asserted-by":"publisher","first-page":"1558","DOI":"10.1109\/PROC.1977.10770","volume":"65","author":"JB Allen","year":"1977","unstructured":"Allen, J.B., Rabiner, L.R.: A unified approach to short-time fourier analysis and synthesis. Proc. IEEE 65(11), 1558\u20131564 (1977)","journal-title":"Proc. IEEE"},{"key":"7_CR3","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/MSP.2014.2326181","volume":"32","author":"D Barchiesi","year":"2015","unstructured":"Barchiesi, D., Giannoulis, D., Stowell, D., Plumbley, M.D.: Acoustic scene classification: classifying environments from the sounds they produce. Signal Process. Mag. IEEE 32, 16\u201334 (2015). https:\/\/doi.org\/10.1109\/MSP.2014.2326181","journal-title":"Signal Process. Mag. IEEE"},{"issue":"5","key":"7_CR4","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1109\/18.57199","volume":"36","author":"I Daubechies","year":"1990","unstructured":"Daubechies, I.: The wavelet transform, time-frequency localization and signal analysis. IEEE Trans. Inf. Theory 36(5), 961\u20131005 (1990)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Davis, S., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences (1980)","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"7_CR6","unstructured":"Enqing, D., Guizhong, L., Yatong, Z., Yu, C.: Voice activity detection based on short-time energy and noise spectrum adaptation. In: 6th International Conference on Signal Processing, 2002, vol. 1, pp. 464\u2013467. IEEE (2002)"},{"key":"7_CR7","unstructured":"Gouyon, F., Pachet, F., Delerue, O., et al.: On the use of zero-crossing rate for an application of classification of percussive sounds. In: Proceedings of the COST G-6 Conference on Digital Audio Effects (DAFX-00), Verona, Italy, p. 26 (2000)"},{"key":"7_CR8","volume-title":"Linear Predictive Coding and the Internet Protocol","author":"RM Gray","year":"2010","unstructured":"Gray, R.M.: Linear Predictive Coding and the Internet Protocol. Now Publishers, Boston (2010)"},{"issue":"1","key":"7_CR9","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1109\/TNN.2002.806626","volume":"14","author":"G Guo","year":"2003","unstructured":"Guo, G., Li, S.Z.: Content-based audio classification and retrieval by support vector machines. IEEE Trans. Neural Netw. 14(1), 209\u2013215 (2003)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"4","key":"7_CR10","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1121\/1.399423","volume":"87","author":"H Hermansky","year":"1990","unstructured":"Hermansky, H.: Perceptual linear predictive (PLP) analysis of speech. J. Acoust. Soc. Am. 87(4), 1738\u20131752 (1990)","journal-title":"J. Acoust. Soc. Am."},{"issue":"4","key":"7_CR11","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1109\/89.326616","volume":"2","author":"H Hermansky","year":"1994","unstructured":"Hermansky, H., Morgan, N.: Rasta processing of speech. IEEE Trans. Speech Audio Process. 2(4), 578\u2013589 (1994)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"6","key":"7_CR12","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82\u201397 (2012). https:\/\/doi.org\/10.1109\/MSP.2012.2205597","journal-title":"IEEE Signal Process. Mag."},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Kons, Z., Toledo-Ronen, O.: Audio event classification using deep neural networks, pp. 1482\u20131486, January 2013","DOI":"10.21437\/Interspeech.2013-384"},{"key":"7_CR14","unstructured":"Lee, H., Pham, P., Largman, Y., Ng, A.Y.: Unsupervised feature learning for audio classification using convolutional deep belief networks. In: Advances in Neural Information Processing Systems, pp. 1096\u20131104 (2009)"},{"issue":"5","key":"7_CR15","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1109\/89.861383","volume":"8","author":"SZ Li","year":"2000","unstructured":"Li, S.Z.: Content-based audio classification and retrieval using the nearest feature line method. IEEE Trans. Speech Audio Process. 8(5), 619\u2013625 (2000)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"1\u20132","key":"7_CR16","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1023\/A:1008066223044","volume":"20","author":"Z Liu","year":"1998","unstructured":"Liu, Z., Wang, Y., Chen, T.: Audio feature extraction and analysis for scene segmentation and classification. J. VLSI Signal Process. Syst. Signal Image Video Technol. 20(1\u20132), 61\u201379 (1998)","journal-title":"J. VLSI Signal Process. Syst. Signal Image Video Technol."},{"key":"7_CR17","first-page":"1","volume":"270","author":"B Logan","year":"2000","unstructured":"Logan, B., et al.: Mel frequency cepstral coefficients for music modeling. ISMIR 270, 1\u201311 (2000)","journal-title":"ISMIR"},{"key":"7_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, September 2015. https:\/\/doi.org\/10.1109\/MLSP.2015.7324337","DOI":"10.1109\/MLSP.2015.7324337"},{"issue":"3","key":"7_CR19","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s10844-017-0481-4","volume":"51","author":"G Roma","year":"2017","unstructured":"Roma, G., Herrera, P., Nogueira, W.: Environmental sound recognition using short-time feature aggregation. J. Intell. Inf. Syst. 51(3), 457\u2013475 (2017). https:\/\/doi.org\/10.1007\/s10844-017-0481-4","journal-title":"J. Intell. Inf. Syst."},{"issue":"4","key":"7_CR20","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/j.specom.2011.11.004","volume":"54","author":"M Sahidullah","year":"2012","unstructured":"Sahidullah, M., Saha, G.: Design, analysis and experimental evaluation of block based transformation in mfcc computation for speaker recognition. Speech Commun. 54(4), 543\u2013565 (2012)","journal-title":"Speech Commun."},{"key":"7_CR21","unstructured":"Sawhney, N., Maes, P.: Situational awareness from environmental sounds. Project Report for Pattie Maes, pp. 1\u20137 (1997)"},{"issue":"4","key":"7_CR22","doi-asserted-by":"publisher","first-page":"998","DOI":"10.1109\/78.492555","volume":"44","author":"RG Stockwell","year":"1996","unstructured":"Stockwell, R.G., Mansinha, L., Lowe, R.: Localization of the complex spectrum: the S transform. IEEE Trans. Signal Process. 44(4), 998\u20131001 (1996)","journal-title":"IEEE Trans. Signal Process."}],"container-title":["Lecture Notes in Computer Science","Transactions on Edutainment XVI"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-662-61510-2_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T01:50:49Z","timestamp":1666317049000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-662-61510-2_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783662615096","9783662615102"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-662-61510-2_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"12 April 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}