{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T13:39:33Z","timestamp":1762522773640,"version":"3.37.3"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T00:00:00Z","timestamp":1668124800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T00:00:00Z","timestamp":1668124800000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s11042-022-14192-1","type":"journal-article","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T04:31:13Z","timestamp":1668141073000},"page":"16395-16408","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Acoustic scene classification with multi-temporal complex modulation spectrogram features and a convolutional LSTM network"],"prefix":"10.1007","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1174-2280","authenticated-orcid":false,"given":"Sayeh","family":"Mirzaei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iman Khani","family":"Jazani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"14192_CR1","doi-asserted-by":"crossref","unstructured":"Ahmadi S, Ahadi SM, Cranen B, Boves L (2014) Sparse coding of the modulation spectrum for noise-robust automatic speech recognition. EURASIP J Audio Speech Music Process vol 2014, no 1, p 36","DOI":"10.1186\/s13636-014-0036-3"},{"key":"14192_CR2","doi-asserted-by":"crossref","unstructured":"Baby D, Virtanen T, Gemmeke JF, Barker T, Hamme HV (2014) Exemplar-based noise robust automatic speech recognition using modulation spectrogram features. In 2014 IEEE Spoken Language Technology Workshop (SLT), pp 519\u2013524","DOI":"10.1109\/SLT.2014.7078628"},{"key":"14192_CR3","doi-asserted-by":"crossref","unstructured":"Barker T, Virtanen T (2013) Non-negative tensor factorisation of modulation spectrograms for monaural sound source separation. In Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013), 25\u201329 August, Lyon, France, pp 827\u2013831","DOI":"10.21437\/Interspeech.2013-236"},{"issue":"12","key":"14192_CR4","doi-asserted-by":"publisher","first-page":"2377","DOI":"10.1109\/TASLP.2016.2602546","volume":"24","author":"T Barker","year":"2016","unstructured":"Barker T, Virtanen T (2016) Blind separation of audio mixtures through nonnegative tensor factorization of modulation spectrograms. IEEEACM Trans Audio Speech Lang Process 24(12):2377\u20132389","journal-title":"IEEEACM Trans Audio Speech Lang Process"},{"key":"14192_CR5","doi-asserted-by":"crossref","unstructured":"Chollet F (2016) Xception: deep learning with depthwise separable convolutions. 2017 IEEE Conf Comput Vis Pattern Recognit CVPR, pp 1800\u20131807","DOI":"10.1109\/CVPR.2017.195"},{"key":"14192_CR6","doi-asserted-by":"publisher","unstructured":"Chung Y-A, Wu C-C, Shen C-H, Lee H-Y, Lee L-S (2016) Audio Word2Vec: unsupervised learning of audio segment representations using sequence-to-sequence autoencoder.\u00a0arXiv preprint arXiv:1603.00982. https:\/\/doi.org\/10.48550\/arXiv.1603.00982","DOI":"10.48550\/arXiv.1603.00982"},{"key":"14192_CR7","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L, Li K, Li F-F (2009) ImageNet: a large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"14192_CR8","unstructured":"Giannoulis D, Stowell D, Benetos E, Rossignol M, Lagrange M, Plumbley MD (2013) A database and challenge for acoustic scene classification and event detection. In 21st European Signal Processing Conference (EUSIPCO 2013), pp 1\u20135"},{"key":"14192_CR9","doi-asserted-by":"crossref","unstructured":"Greenberg S, Kingsbury BED (1997) The modulation spectrogram: in pursuit of an invariant representation of speech. In 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol 3, pp 1647\u20131650","DOI":"10.1109\/ICASSP.1997.598826"},{"key":"14192_CR10","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Presented at the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"14192_CR11","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, van der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. Presented at the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"issue":"1","key":"14192_CR12","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/S0167-6393(98)00032-6","volume":"25","author":"BED Kingsbury","year":"1998","unstructured":"Kingsbury BED, Morgan N, Greenberg S (1998) Robust speech recognition using the modulation spectrogram. Speech Commun 25(1):117\u2013132","journal-title":"Speech Commun"},{"key":"14192_CR13","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.sigpro.2014.05.019","volume":"105","author":"S K\u0131rb\u0131z","year":"2014","unstructured":"K\u0131rb\u0131z S, G\u00fcnsel B (2014) A multiresolution non-negative tensor factorization approach for single channel sound source separation. Signal Process 105:56\u201369","journal-title":"Signal Process"},{"issue":"2","key":"14192_CR14","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/s11859-018-1308-z","volume":"23","author":"L Lu","year":"2018","unstructured":"Lu L, Yang Y, Jiang Y, Ai H, Tu W (2018) Shallow convolutional neural networks for acoustic scene classification. Wuhan Univ J Nat Sci 23(2):178\u2013184","journal-title":"Wuhan Univ J Nat Sci"},{"key":"14192_CR15","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.sigpro.2017.07.013","volume":"142","author":"S Masaya","year":"2018","unstructured":"Masaya S (2018) Audio signal separation through complex tensor factorization: utilizing modulation frequency and phase information. Signal Process 142:137\u2013148","journal-title":"Signal Process"},{"key":"14192_CR16","doi-asserted-by":"crossref","unstructured":"Mesaros A, Heittola T, Virtanen T (2016) TUT database for acoustic scene classification and sound event detection. In 2016 24th European Signal Processing Conference (EUSIPCO), pp 1128\u20131132","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"14192_CR17","unstructured":"Mesaros A et al (2017) DCASE 2017 Challenge setup: Tasks, datasets and baseline system"},{"key":"14192_CR18","doi-asserted-by":"crossref","unstructured":"Moritz N, Anem\u00fcller J, Kollmeier B (2011) Amplitude modulation spectrogram based features for robust speech recognition in noisy and reverberant environments. In 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 5492\u20135495","DOI":"10.1109\/ICASSP.2011.5947602"},{"key":"14192_CR19","doi-asserted-by":"crossref","unstructured":"Phan H, Koch P, Katzberg F, Maass M, Mazur R, Mertins A (2017) Audio scene classification with deep recurrent neural networks. In Interspeech 2017, pp 3043\u20133047","DOI":"10.21437\/Interspeech.2017-101"},{"key":"14192_CR20","unstructured":"Shi X, Chen Z, Wang H, Yeung D-Y, Wong W, Woo W (2015) Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In advances in neural information processing systems 28, Cortes C, Lawrence ND, Lee DD, Sugiyama M, Garnett R Eds. Curran Associates, Inc, pp 802\u2013810"},{"key":"14192_CR21","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. CoRR, vol. abs\/1409.1556"},{"key":"14192_CR22","doi-asserted-by":"crossref","unstructured":"Valenti M, Squartini S, Diment A, Parascandolo G, Virtanen T (2017) A convolutional neural network approach for acoustic scene classification. In 2017 International Joint Conference on Neural Networks (IJCNN), pp 1547\u20131554","DOI":"10.1109\/IJCNN.2017.7966035"},{"key":"14192_CR23","doi-asserted-by":"publisher","first-page":"012037","DOI":"10.1088\/1742-6596\/1169\/1\/012037","volume":"1169","author":"D Wang","year":"2019","unstructured":"Wang D, Zhang L, Xu K, Wang Y (2019) Acoustic scene classification based on dense convolutional networks incorporating multi-channel features. J Phys Conf Ser 1169:012037","journal-title":"J Phys Conf Ser"},{"issue":"5","key":"14192_CR24","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1016\/j.specom.2010.08.013","volume":"53","author":"S Wu","year":"2011","unstructured":"Wu S, Falk TH, Chan W-Y (2011) Automatic speech emotion recognition using modulation spectral features. Speech Commun 53(5):768\u2013785","journal-title":"Speech Commun"},{"key":"14192_CR25","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.eswa.2019.01.085","volume":"126","author":"J Xie","year":"2019","unstructured":"Xie J, Zhu M (2019) Investigation of acoustic and visual features for acoustic scene classification. Expert Syst Appl 126:20\u201329","journal-title":"Expert Syst Appl"},{"key":"14192_CR26","doi-asserted-by":"crossref","unstructured":"Xu J, Lin T, Yu T, Tai T, Chang P (2018) Acoustic scene classification using reduced mobilenet architecture. In 2018 IEEE International Symposium on Multimedia (ISM), pp 267\u2013270","DOI":"10.1109\/ISM.2018.00038"},{"key":"14192_CR27","doi-asserted-by":"crossref","unstructured":"Xu K et al (2018) Mixup-based acoustic scene classification using multi-channel convolutional neural network. In Advances in Multimedia Information Processing \u2013 PCM 2018, pp 14\u201323","DOI":"10.1007\/978-3-030-00764-5_2"},{"key":"14192_CR28","doi-asserted-by":"crossref","unstructured":"Yang Y et al (2019) Kullback\u2013Leibler divergence frequency warping scale for acoustic scene classification using convolutional neural network. In ICASSP 2019\u20132019 IEEE international conference on acoustics, Speech and Signal Processing (ICASSP), pp 840\u2013844","DOI":"10.1109\/ICASSP.2019.8683000"},{"key":"14192_CR29","unstructured":"Zeinali H, Burget L, Cernocky JH (2018) Convolutional neural networks and x-vector embedding for DCASE2018 Acoustic Scene Classification challenge. In Proceedings of the Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE2018), pp 202\u2013206"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-14192-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-14192-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-14192-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T09:32:25Z","timestamp":1681551145000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-14192-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,11]]},"references-count":29,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["14192"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-14192-1","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2022,11,11]]},"assertion":[{"value":"13 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 September 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2022","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 have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}