{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T19:38:20Z","timestamp":1771270700456,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":44,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819947416","type":"print"},{"value":"9789819947423","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-981-99-4742-3_6","type":"book-chapter","created":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T00:02:38Z","timestamp":1690675358000},"page":"70-84","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Effective Audio Classification Network Based on Paired Inverse Pyramid Structure and Dense MLP Block"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8134-2314","authenticated-orcid":false,"given":"Yunhao","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunjie","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihui","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianlu","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lifang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,30]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Salamon, J., Jacoby, C., Bello, J.P.: A dataset and taxonomy for urban sound research. In: Proceedings ACM International Conference on Multimedia, pp. 1041\u20131044 (2014)","DOI":"10.1145\/2647868.2655045"},{"issue":"5","key":"6_CR2","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TSA.2002.800560","volume":"10","author":"G Tzanetakis","year":"2002","unstructured":"Tzanetakis, G., Cook, P.: Musical genre classifcation of audio signals. IEEE Trans. Speech Audio Process. 10(5), 293\u2013302 (2002). https:\/\/doi.org\/10.1109\/TSA.2002.800560","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"8","key":"6_CR3","doi-asserted-by":"publisher","first-page":"2249","DOI":"10.1109\/TASL.2007.905139","volume":"15","author":"E Alexandre","year":"2007","unstructured":"Alexandre, E., et al.: Feature selection for sound classification in hearing aids through restricted search driven by genetic algorithms. IEEE Trans. Audio Speech Lang. Process. 15(8), 2249\u20132256 (2007). https:\/\/doi.org\/10.1109\/TASL.2007.905139","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"3","key":"6_CR4","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.D., Stowell, D., Plumbley, M.D.: Acoustic scene classification: classifying environments from the sounds they produce. IEEE Signal Process. Mag. 32(3), 16\u201334 (2015). https:\/\/doi.org\/10.1109\/MSP.2014.2326181","journal-title":"IEEE Signal Process. Mag."},{"key":"6_CR5","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/J.APACOUST.2016.11.016","volume":"119","author":"FR Gonz\u00e1lez-Hern\u00e1ndez","year":"2017","unstructured":"Gonz\u00e1lez-Hern\u00e1ndez, F.R., et al.: Marine mammal sound classification based on a parallel recognition model and octave analysis. Appl. Acoust. 119, 17\u201328 (2017). https:\/\/doi.org\/10.1016\/J.APACOUST.2016.11.016","journal-title":"Appl. Acoust."},{"key":"6_CR6","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s11042-011-0742-0","volume":"59","author":"AS Lampropoulos","year":"2012","unstructured":"Lampropoulos, A.S., Lampropoulou, P.S., Tsihrintzis, G.A.: A cascade-hybrid music recommender system for mobile services based on musical genre classification and personality diagnosis. Multimedia Tools Appl. 59, 241\u2013258 (2012)","journal-title":"Multimedia Tools Appl."},{"issue":"5","key":"6_CR7","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1007\/s10597-020-00560-4","volume":"56","author":"MJ Silverman","year":"2020","unstructured":"Silverman, M.J.: Music-based affect regulation and unhealthy music use explain coping strategies in adults with mental health conditions. Community Ment. Health J. 56(5), 939\u2013946 (2020). https:\/\/doi.org\/10.1007\/s10597-020-00560-4","journal-title":"Community Ment. Health J."},{"issue":"3","key":"6_CR8","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/LSP.2017.2657381","volume":"24","author":"J Salamon","year":"2017","unstructured":"Salamon, J., Bello, J.P.: Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process. Lett. 24(3), 279\u2013283 (2017)","journal-title":"IEEE Signal Process. Lett."},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: Acoustic scene classification using deep learning-based ensemble averaging. In: Proceedings of Detection Classification Acoustic Scenes Events Workshop (2019)","DOI":"10.33682\/8rd2-g787"},{"key":"6_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1007\/978-3-319-69900-4_40","volume-title":"Pattern Recognition and Machine Intelligence","author":"RN Tak","year":"2017","unstructured":"Tak, R.N., Agrawal, D.M., Patil, H.A.: Novel phase encoded mel filterbank energies for environmental sound classification. In: Shankar, B.U., Ghosh, K., Mandal, D.P., Ray, S.S., Zhang, D., Pal, S.K. (eds.) PReMI 2017. LNCS, vol. 10597, pp. 317\u2013325. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-69900-4_40"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Kumar, A., Khadkevich, M., F\u00fcgen, C.: Knowledge transfer from weakly labeled audio using convolutional neural network for sound events and scenes. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 326\u2013330 (2018)","DOI":"10.1109\/ICASSP.2018.8462200"},{"key":"6_CR12","unstructured":"Kumar, A., Ithapu, V.: A sequential self teaching approach for improving generalization in sound event recognition. In: Proceedings of 37th International Conference on Machine Learning, pp. 5447\u20135457 (2020)"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Aytar, Y., Vondrick, C., Torralba, A.: SoundNet: learning sound representations from unlabeled video. In: Proceedings of 30th International Conference on Neural Information Processing Systems, pp. 892\u2013900 (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"6_CR14","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/TASLP.2020.2966868","volume":"28","author":"L Zhang","year":"2020","unstructured":"Zhang, L., Shi, Z., Han, J.: Pyramidal temporal pooling with discriminative mapping for audio classification. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 770\u2013784 (2020)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"6_CR15","doi-asserted-by":"publisher","first-page":"950","DOI":"10.1109\/LSP.2020.2996085","volume":"27","author":"L Zhang","year":"2020","unstructured":"Zhang, L., Han, J., Shi, Z.: Learning temporal relations from semantic neighbors for acoustic scene classification. IEEE Signal Process. Lett. 27, 950\u2013954 (2020)","journal-title":"IEEE Signal Process. Lett."},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, L., Han, J., Shi, Z.: ATReSN-Net: capturing attentive temporal relations in semantic neighborhood for acoustic scene classification. In: Proceedings of Annual Conference of the International Speech Communication Association, pp. 1181\u20131185 (2020)","DOI":"10.21437\/Interspeech.2020-1151"},{"key":"6_CR17","unstructured":"Ilya, T., et al.: MLP-mixer: an all-MLP architecture for vision. In: Neural Information Processing Systems, pp. 24261\u201324272 (2021)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical lmage database. In: CVPR 2009 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A ConvNet for the 2020s. In: Computer Vision and Pattern Recognition, pp. 11966\u201311976 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., J\u00e9gou, H.: Going deeper with image transformers. In: International Conference on Computer Vision, pp. 32\u201342 (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"6_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-319-46493-0_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Huang","year":"2016","unstructured":"Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646\u2013661. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR23","unstructured":"Lei, J.B., Ryan, K., Geoffrey, E.H., Jimmy, L.B., Jamie, R.K., et al.: Layer normalization. Computing Research Repository, abs\/1607.06450 (2016)"},{"key":"6_CR24","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian Error Linear Units (GELUs). arXiv.org (2022). https:\/\/arxiv.org\/abs\/1606.08415. Accessed 15 Sept 2022"},{"key":"6_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS 2017), pp. 6000\u20136010. Curran Associates Inc., Red Hook (2017)"},{"key":"6_CR26","doi-asserted-by":"publisher","first-page":"56","DOI":"10.3844\/jcssp.2016.56.61","volume":"12","author":"Y Zouhir","year":"2016","unstructured":"Zouhir, Y., Ouni, K.: Feature extraction method for improving speech recognition in noisy environments. J. Comput. Sci. 12, 56\u201361 (2016). https:\/\/doi.org\/10.3844\/jcssp.2016.56.61","journal-title":"J. Comput. Sci."},{"issue":"6","key":"6_CR27","doi-asserted-by":"publisher","first-page":"1684","DOI":"10.1109\/TMM.2012.2199972","volume":"14","author":"X Valero","year":"2012","unstructured":"Valero, X., Alias, F.: Gammatone cepstral coefficients: biologically inspired features for non-speech audio classification. IEEE Trans. Multimedia 14(6), 1684\u20131689 (2012). https:\/\/doi.org\/10.1109\/TMM.2012.2199972","journal-title":"IEEE Trans. Multimedia"},{"key":"6_CR28","doi-asserted-by":"publisher","unstructured":"Zhou, X., et al.: Linear versus mel frequency cepstral coefficients for speaker recognition. In: 2011 IEEE Workshop on Automatic Speech RecognitionUnderstanding, pp. 559\u2013564 (2011). https:\/\/doi.org\/10.1109\/ASRU.2011.6163888","DOI":"10.1109\/ASRU.2011.6163888"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Kumar, C., et al.: Analysis of MFCC and BFCC in a speaker identification system. In: 2018 International Conference on Computing, Mathematics and Engineering Technologies (2018)","DOI":"10.1109\/ICOMET.2018.8346330"},{"key":"6_CR30","unstructured":"Alexey, D., Lucas, B., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Xu, W., Xu, Y., Chang, T., Tu, Z.: Co-scale conv-attentional image transformers. In: International Conference on Computer Vision, pp. 9961\u20139970 (2021)","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"6_CR32","unstructured":"St\u00e9phane, D., Hugo, T., et al.: Convit: improving vision transformers with soft convolutional inductive biases. In: International Conference on Machine Learning, vol. 139 pp. 2286\u20132296 (2021)"},{"key":"6_CR33","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1007\/978-3-031-20053-3_30","volume-title":"ECCV 2022","author":"H Touvron","year":"2022","unstructured":"Touvron, H., Cord, M., J\u00e9gou, H.: DeiT III: revenge of the ViT. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, pp. 516\u2013533. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20053-3_30"},{"key":"6_CR34","unstructured":"Hedegaard, L., Bakhtiarnia, A., Iosifidis, A.: Continual Transformers: Redundancy-Free Attention for Online Inference, arXiv.org (2022). https:\/\/arxiv.org\/abs\/2201.06268"},{"key":"6_CR35","unstructured":"Liu, C., Feng, L., Liu, G., Wang, H., Liu, S.: Bottom-up Broadcast Neural Network for Music Genre Classification, arXiv.org (2022). https:\/\/arxiv.org\/abs\/1901.08928"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Heakl, A., Abdelgawad, A., Parque, V.: A study on broadcast networks for music genre classification. In: IEEE International Joint Conference on Neural Network, pp. 1\u20138 (2022)","DOI":"10.1109\/IJCNN55064.2022.9892651"},{"key":"6_CR37","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1109\/LSP.2022.3150258","volume":"29","author":"B Bahmei","year":"2022","unstructured":"Bahmei, B., et al.: CNN-RNN and data augmentation using deep convolutional generative adversarial network for environmental sound classification. IEEE Signal Process. Lett. 29, 682\u2013686 (2022)","journal-title":"IEEE Signal Process. Lett."},{"key":"6_CR38","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/LSP.2021.3130502","volume":"29","author":"H Song","year":"2022","unstructured":"Song, H., Deng, S., Han, J.: Exploring inter-node relations in CNNs for environmental sound classification. IEEE Signal Process. Lett. 29, 154\u2013158 (2022)","journal-title":"IEEE Signal Process. Lett."},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhu, Y., Yan, Z., Chen, L.: Effective Audio Classification Network Based on Paired Inverse Pyramid Structure and Dense MLP Block (2022)","DOI":"10.1007\/978-981-99-4742-3_6"},{"key":"6_CR40","unstructured":"Wightman, R.: PyTorch Image Models (2019). https:\/\/github.com\/rwightman\/pytorch-image-models"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Fonseca, E., et al.: Audio tagging with noisy labels and minimal supervision.In: Proceedings of DCASE2019 Workshop, NYC, US (2019)","DOI":"10.33682\/w13e-5v06"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Woo, S., et al.: ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders. arXiv abs\/2301.00808 (2023)","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Gong, Y., Chung, Y.-A., Glass, J.R.: AST: Audio spectrogram transformer. In: Interspeech (2021)","DOI":"10.21437\/Interspeech.2021-698"},{"key":"6_CR44","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Data Augmentation for Environmental Sound Classification Using Diffusion Probabilistic Model with Top-K Selection Discriminator. arXiv:2023.15161 (2023)","DOI":"10.1007\/978-981-99-4742-3_23"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-4742-3_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T03:02:14Z","timestamp":1702868534000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-4742-3_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819947416","9789819947423"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-4742-3_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"30 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2023a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2023\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}