{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T14:44:34Z","timestamp":1774968274316,"version":"3.50.1"},"reference-count":42,"publisher":"Allerton Press","issue":"4","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"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":["Aut. Control Comp. Sci."],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.3103\/s0146411621040106","type":"journal-article","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T09:01:43Z","timestamp":1630659703000},"page":"311-318","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Convolutional Neural Network-Gated Recurrent Unit Neural Network with Feature Fusion for Environmental Sound Classification"],"prefix":"10.3103","volume":"55","author":[{"family":"Yu Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinfang","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youming","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Da","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1627","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"7355_CR1","doi-asserted-by":"crossref","unstructured":"Baum, E., Harper, M., Alicea, R., and Ordonez, C., Sound identification for fire-fighting mobile robots, 2018 Second IEEE Int. Conf. Rob. Comput. (IRC), 2018, pp. 79\u201386.","DOI":"10.1109\/IRC.2018.00020"},{"key":"7355_CR2","doi-asserted-by":"crossref","unstructured":"Liu, J.M., You, M., Li, G.Z., Wang, Z., Xu, X., Qiu, Z., Xie, W., An, C., and Chen, S., Cough signal recognition with Gammatone cepstral coefficients, IEEE China Summit Int. Conf. Signal Inf. Process., 2013, pp. 160\u2013164.","DOI":"10.1109\/ChinaSIP.2013.6625319"},{"key":"7355_CR3","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/s00521-016-2501-7","volume":"29","author":"H. Ali","year":"2018","unstructured":"Ali, H., Tran, S.N., Benetos, E., and d\u2019Avila Garcez, A.S., Speaker recognition with hybrid features from a deep belief network, Neural Comput. Appl., 2018, vol. 29, no. 6, pp. 13\u201319.","journal-title":"Neural Comput. Appl."},{"key":"7355_CR4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2045","volume-title":"Music genre recognition using deep neural networks and transfer learning","author":"D. Ghosal","year":"2018","unstructured":"Ghosal, D. and Kolekar, M.H., Music genre recognition using deep neural networks and transfer learning, Interspeech, 2018, pp. 2087\u20132091."},{"key":"7355_CR5","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. and Saha, G., Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition, Speech Commun., 2012, vol. 54, no. 4, pp. 543\u2013565.","journal-title":"Speech Commun."},{"key":"7355_CR6","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1109\/TASL.2009.2017438","volume":"17","author":"S. Chu","year":"2009","unstructured":"Chu, S., Narayanan, S., and Kuo, C.C.J., Environmental sound recognition with time-frequency audio features, IEEE Trans. Audio Speech Lang. Process., 2009, vol. 17, no. 6, pp. 1142\u20131158.","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"7355_CR7","doi-asserted-by":"publisher","first-page":"1684","DOI":"10.1109\/TMM.2012.2199972","volume":"14","author":"X. Valero","year":"2012","unstructured":"Valero, X. and Alias, F., Gammatone cepstral coefficients: Biologically inspired features for non-speech audio classification, IEEE Trans. Multimedia, 2012, vol. 14, no. 6, pp. 1684\u20131689.","journal-title":"IEEE Trans. Multimedia"},{"key":"7355_CR8","doi-asserted-by":"crossref","unstructured":"Geiger, J.T. and Helwani, K., Improving event detection for audio surveillance using Gabor filterbank features, 23rd Eur. Signal Process. Conf., 2015, pp. 714\u2013718.","DOI":"10.1109\/EUSIPCO.2015.7362476"},{"key":"7355_CR9","doi-asserted-by":"crossref","unstructured":"Jin, Z., Zhou, G., Gao, D., and Zhang, Y., EEG classification using sparse Bayesian extreme learning machine for brain\u2013computer interface, Neural Comput. Appl., 2018, pp. 1\u20139.","DOI":"10.1007\/s00521-018-3735-3"},{"key":"7355_CR10","doi-asserted-by":"crossref","unstructured":"Shao, Y. and Wang, D., Robust speaker identification using auditory features and computational auditory scene analysis, Proc. IEEE Int. Conf. Acoust. Speech Signal Process., 2008, pp. 1589\u20131592.","DOI":"10.1109\/ICASSP.2008.4517928"},{"key":"7355_CR11","doi-asserted-by":"crossref","unstructured":"Wang, J.C., Wang, J.F., He, K.W., and Hsu, C.S., Environmental sound classification using hybrid SVM\/KNN classifier and MPEG-7 audio low-level descriptor, Proc. Int. Jt. Conf. Neural Netw., 2006, pp. 1731\u20131735.","DOI":"10.1109\/IJCNN.2006.246644"},{"key":"7355_CR12","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1016\/j.eswa.2017.12.015","volume":"96","author":"Y. Zhang","year":"2018","unstructured":"Zhang, Y., Wang, Y., Zhou, G., Jin, J., Wang, B., Wang, X., and Cichocki, A., Multi-kernel extreme learning machine for EEG classification in brain-computer interfaces, Expert Syst. Appl., 2018, vol. 96, pp. 302\u2013310.","journal-title":"Expert Syst. Appl."},{"key":"7355_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, H., McLoughlin, I., and Song, Y., Robust sound event recognition using convolutional neural networks, Proc. IEEE Int. Conf. Acoust. Speech Signal Process., 2015, pp. 559\u2013563.","DOI":"10.1109\/ICASSP.2015.7178031"},{"key":"7355_CR14","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y. LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., and Hinton, G., Deep learning, Nature, 2015, vol. 521, no. 7553, pp. 436\u2013444.","journal-title":"Nature"},{"key":"7355_CR15","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E., Imagenet classification with deep convolutional neural networks, Adv. Neural Inf. Process. Syst., 2012, pp. 1097\u20131105."},{"key":"7355_CR16","volume-title":"Analysis of CNN-based speech recognition system using raw speech as input","author":"D. Palaz","year":"2015","unstructured":"Palaz, D., Magimai.-Doss, M., and Collobert, R., Analysis of CNN-based speech recognition system using raw speech as input, IDIAP, 2015."},{"key":"7355_CR17","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., and Bengio, Y., On the properties of neural machine translation: Encoder-decoder approaches, arXiv:1409.1259."},{"key":"7355_CR18","doi-asserted-by":"crossref","unstructured":"Piczak, K.J., ESC: Dataset for environmental sound classification, 23rd ACM Int. Conf. Multimedia, 2015, pp.\u00a01015\u20131018.","DOI":"10.1145\/2733373.2806390"},{"key":"7355_CR19","doi-asserted-by":"crossref","unstructured":"Salamon, J., Jacoby, C., and Bello, J.P., A dataset and taxonomy for urban sound research, 22nd ACM Int. Conf. Multimedia, 2014, pp. 1041\u20131044.","DOI":"10.1145\/2647868.2655045"},{"key":"7355_CR20","doi-asserted-by":"crossref","unstructured":"Piczak, K.J., Environmental sound classification with convolutional neural networks, IEEE Int. Workshop Mach. Learn. Signal Process., 2015, pp. 1\u20136.","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"7355_CR21","volume-title":"Acoustic scene and event recognition using recurrent neural networks","author":"T.H. Vu","year":"2016","unstructured":"Vu, T.H. and Wang, J.C., Acoustic scene and event recognition using recurrent neural networks, Detection and Classification of Acoustic Scenes and Events, 2016."},{"key":"7355_CR22","volume-title":"Acoustic scene classification using parallel combination of LSTM and CNN","author":"S.H. Bae","year":"2016","unstructured":"Bae, S.H., Choi, I., and Kim, N.S., Acoustic scene classification using parallel combination of LSTM and CNN, Detection and Classification of Acoustic Scenes and Events, 2016, pp. 11\u201315."},{"key":"7355_CR23","unstructured":"Aytar, Y., Vondrick, C., and Torralba, A., Soundnet: Learning sound representations from unlabeled video, Adv. Neural Inf. Process. Syst., 2016, pp. 892\u2013900."},{"key":"7355_CR24","doi-asserted-by":"crossref","unstructured":"Dai, W., Dai, C., Qu, S., Li, J., and Das, S., Very deep convolutional neural networks for raw waveforms, Proc. IEEE Int. Conf. Acoust. Speech Signal Process., 2017, pp. 421\u2013425.","DOI":"10.1109\/ICASSP.2017.7952190"},{"key":"7355_CR25","doi-asserted-by":"crossref","unstructured":"Tokozume, Y. and Harada, T., Learning environmental sounds with end-to-end convolutional neural network, Proc. IEEE Int. Conf. Acoust. Speech Signal Process., 2017, pp. 2721\u20132725.","DOI":"10.1109\/ICASSP.2017.7952651"},{"key":"7355_CR26","unstructured":"Tokozume, Y., Ushiku, Y., and Harada, T., Learning from between-class examples for deep sound recognition, arXiv:1711.10282"},{"key":"7355_CR27","doi-asserted-by":"crossref","unstructured":"Sang, J., Park, S., and Lee, J., Convolutional recurrent neural networks for urban sound classification using raw waveforms, 26th Eur. Signal Process. Conf., 2018, pp. 2444\u20132448.","DOI":"10.23919\/EUSIPCO.2018.8553247"},{"key":"7355_CR28","doi-asserted-by":"publisher","first-page":"130327","DOI":"10.1109\/ACCESS.2019.2939495","volume":"7","author":"Z. Zhang","year":"2019","unstructured":"Zhang, Z., Xu, S., Zhang, S., Qiao, T., and Cao, S., Learning attentive representations for environmental sound classification, IEEE Access, 2019, vol. 7, pp. 130327\u2013130339.","journal-title":"IEEE Access"},{"key":"7355_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xu, S., Qiao, T., Zhang, S., and Cao, S., Attention based convolutional recurrent neural network for environmental sound classification, Chinese Conf. Pattern Recognition Computer Vision, 2019, pp. 261\u2013271.","DOI":"10.1007\/978-3-030-31654-9_23"},{"key":"7355_CR30","unstructured":"Takahashi, N., Gygli, M., Pfister, B., and Van Gool, L., Deep convolutional neural networks and data augmentation for acoustic event detection, arXiv:1604.07160"},{"key":"7355_CR31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-831","volume-title":"Unsupervised filterbank learning using convolutional restricted Boltzmann machine for environmental sound classification","author":"H.B. Sailor","year":"2017","unstructured":"Sailor, H.B., Agrawal, D.M., and Patil, H.A., Unsupervised filterbank learning using convolutional restricted Boltzmann machine for environmental sound classification, Interspeech, 2017, pp. 3107\u20133111."},{"key":"7355_CR32","doi-asserted-by":"crossref","unstructured":"Tak, R.N., Agrawal, D.M., and Patil, H.A., Novel phase encoded mel filterbank energies for environmental sound classification, Int. Conf. Pattern Recognit. Mach. Intell., 2017, pp. 317\u2013325.","DOI":"10.1007\/978-3-319-69900-4_40"},{"key":"7355_CR33","doi-asserted-by":"crossref","unstructured":"Agrawal, D.M., Sailor, H.B., Soni, M.H., and Patil, H.A., Novel TEO-based gammatone features for environmental sound classification, 25th Eur. Signal Process. Conf., 2017, pp. 1809\u20131813.","DOI":"10.23919\/EUSIPCO.2017.8081521"},{"key":"7355_CR34","doi-asserted-by":"publisher","first-page":"2048","DOI":"10.1016\/j.procs.2017.08.250","volume":"112","author":"V. Boddapati","year":"2017","unstructured":"Boddapati, V., Petef, A., Rasmusson, J., and Lundberg, L., Classifying environmental sounds using image recognition networks, Procedia Comput. Sci., 2017, vol. 112, pp. 2048\u20132056.","journal-title":"Procedia Comput. Sci."},{"key":"7355_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xu, S., Cao, S., and Zhang, S., Deep convolutional neural network with mixup for environmental sound classification, Chinese Conf. Pattern Recognition Computer Vision, 2018, pp. 356\u2013367.","DOI":"10.1007\/978-3-030-03335-4_31"},{"key":"7355_CR36","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.3390\/s19071733","volume":"19","author":"Y. Su","year":"2019","unstructured":"Su, Y., Zhang, K., Wang, J., and Madani, K., Environment sound classification using a two-stream CNN based on decision-level fusion, Sensors, 2019, vol. 19, no. 7, pp. 1733.","journal-title":"Sensors"},{"key":"7355_CR37","unstructured":"Sharma, J., Granmo, O.C., and Goodwin, M., Environment sound classification using multiple feature channels and deep convolutional neural networks, arXiv:1908.11219"},{"key":"7355_CR38","doi-asserted-by":"crossref","unstructured":"Shao, Y. and Wang, D., Robust speaker identification using auditory features and computational auditory scene analysis, IEEE Int. Conf. Acoust. Speech Signal Process., 2008, pp. 1589\u20131592.","DOI":"10.1109\/ICASSP.2008.4517928"},{"key":"7355_CR39","unstructured":"Xing, Z., Baik, E., Jiao, Y., Kulkarni, N., Li, C., Muralidhar, G., Parandehgheibi, M., Reed, E., Singhal, A., Xiao, F., and Pouliot, C., Modeling of the latent embedding of music using deep neural network, arXiv:1705.05229"},{"key":"7355_CR40","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1121\/1.4864294","volume":"135","author":"B. Gao","year":"2014","unstructured":"Gao, B., Woo, W.L., and Khor, L.C., Cochleagram-based audio pattern separation using two-dimensional non-negative matrix factorization with automatic sparsity adaptation, J. Acoust. Soc. Am., 2014, vol. 135, no. 3, pp. 1171\u20131185.","journal-title":"J. Acoust. Soc. Am."},{"key":"7355_CR41","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.apacoust.2018.05.030","volume":"140","author":"R.V. Sharan","year":"2018","unstructured":"Sharan, R.V. and Moir, T.J., Pseudo-color cochleagram image feature and sequential feature selection for robust acoustic event recognition, Appl. Acoust., 2018, vol. 140, pp. 198\u2013204.","journal-title":"Appl. Acoust."},{"key":"7355_CR42","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1121\/1.400476","volume":"89","author":"J.C. Brown","year":"1991","unstructured":"Brown, J.C., Calculation of a constant Q spectral transform, J. Acoust. Soc. Am., 1991, vol. 89, no. 1, pp. 425\u2013434.","journal-title":"J. Acoust. Soc. Am."}],"container-title":["Automatic Control and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.3103\/S0146411621040106.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.3103\/S0146411621040106","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.3103\/S0146411621040106.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T22:03:44Z","timestamp":1773612224000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.3103\/S0146411621040106"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":42,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["7355"],"URL":"https:\/\/doi.org\/10.3103\/s0146411621040106","relation":{},"ISSN":["0146-4116","1558-108X"],"issn-type":[{"value":"0146-4116","type":"print"},{"value":"1558-108X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7]]},"assertion":[{"value":"19 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"CONFLICT OF INTEREST"}}]}}