{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:01:54Z","timestamp":1764403314715,"version":"3.37.3"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T00:00:00Z","timestamp":1703203200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T00:00:00Z","timestamp":1703203200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100020084","name":"Guangzhou Municipal Science and Technology Bureau","doi-asserted-by":"publisher","award":["202002030133"],"award-info":[{"award-number":["202002030133"]}],"id":[{"id":"10.13039\/501100020084","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s00521-023-09260-y","type":"journal-article","created":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T09:02:42Z","timestamp":1703235762000},"page":"4885-4905","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Fast deep learning with tight frame wavelets"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8626-8686","authenticated-orcid":false,"given":"Haitao","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,22]]},"reference":[{"key":"9260_CR1","doi-asserted-by":"publisher","first-page":"921","DOI":"10.21437\/Interspeech.2022-153","volume":"2022","author":"Z Chen","year":"2022","unstructured":"Chen Z, Zhang P (2022) Lightweight full-band and sub-band fusion network for real time speech enhancement. Proc Interspeech 2022:921\u2013925","journal-title":"Proc Interspeech"},{"key":"9260_CR2","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, vol 30"},{"key":"9260_CR3","doi-asserted-by":"crossref","unstructured":"Zhang S, Lei M, Yan Z, Dai L (2018) Deep-fsmn for large vocabulary continuous speech recognition. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 5869\u20135873","DOI":"10.1109\/ICASSP.2018.8461404"},{"key":"9260_CR4","doi-asserted-by":"crossref","unstructured":"Hu Y, Liu Y, Lv S, Xing M, Zhang S, Fu Y, Wu J, Zhang B, Xie L (2020) Dccrn: Deep complex convolution recurrent network for phase-aware speech enhancement. arXiv preprint arXiv:2008.00264","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"9260_CR5","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-YM (2020) Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934"},{"key":"9260_CR6","doi-asserted-by":"crossref","unstructured":"Duta IC, Liu L, Zhu F, Shao L (2021) Improved residual networks for image and video recognition. In: 2020 25th international conference on pattern recognition (ICPR). IEEE, pp 9415\u20139422","DOI":"10.1109\/ICPR48806.2021.9412193"},{"issue":"1","key":"9260_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000006","volume":"2","author":"Y Bengio","year":"2009","unstructured":"Bengio Y et al (2009) Learning deep architectures for AI. Found Trends Mach Learn 2(1):1\u2013127","journal-title":"Found Trends Mach Learn"},{"key":"9260_CR8","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"9260_CR9","unstructured":"Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler DM, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D (2020) Language models are few-shot learners. arXiv e-prints"},{"issue":"2","key":"9260_CR10","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5(2):157\u2013166","journal-title":"IEEE Trans Neural Netw"},{"key":"9260_CR11","unstructured":"Erhan D, Manzagol P-A, Bengio Y, Bengio S, Vincent P (2009) The difficulty of training deep architectures and the effect of unsupervised pre-training. In: Artificial intelligence and statistics, pp 153\u2013160"},{"key":"9260_CR12","doi-asserted-by":"crossref","unstructured":"LeCun YA, Bottou L, Orr GB, M\u00fcller K-R (2012) Efficient backprop. In: Neural networks: tricks of the trade. Springer, Berlin, pp 9\u201348","DOI":"10.1007\/978-3-642-35289-8_3"},{"issue":"5","key":"9260_CR13","first-page":"1","volume":"34","author":"Y Bengio","year":"2007","unstructured":"Bengio Y, LeCun Y et al (2007) Scaling learning algorithms towards AI. Large-scale Kernel Mach 34(5):1\u201341","journal-title":"Large-scale Kernel Mach"},{"issue":"3","key":"9260_CR14","first-page":"625","volume":"11","author":"D Erhan","year":"2010","unstructured":"Erhan D, Bengio Y, Courville AC, Manzagol PA, Vincent P, Bengio S (2010) Why does unsupervised pre-training help deep learning? J Mach Learn Res 11(3):625\u2013660","journal-title":"J Mach Learn Res"},{"key":"9260_CR15","unstructured":"Dauphin YN, Bengio Y (2013) Big neural networks waste capacity. arXiv preprint arXiv:1301.3583"},{"issue":"1","key":"9260_CR16","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"9260_CR17","unstructured":"Ziegler T, Fritsche M, Kuhn L, Donhauser K (2019) Efficient smoothing of dilated convolutions for image segmentation. arXiv preprint arXiv:1903.07992"},{"issue":"8","key":"9260_CR18","doi-asserted-by":"publisher","first-page":"5455","DOI":"10.1007\/s10462-020-09825-6","volume":"53","author":"A Khan","year":"2020","unstructured":"Khan A, Sohail A, Zahoora U, Qureshi AS (2020) A survey of the recent architectures of deep convolutional neural networks. Artif Intell Rev 53(8):5455\u20135516","journal-title":"Artif Intell Rev"},{"key":"9260_CR19","doi-asserted-by":"crossref","unstructured":"Ma N, Zhang X, Zheng H-T, Sun J (2018) Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: Proceedings of the European conference on computer vision (ECCV), pp 116\u2013131","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"9260_CR20","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"9260_CR21","doi-asserted-by":"crossref","unstructured":"Chollet F (2017) Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1251\u20131258","DOI":"10.1109\/CVPR.2017.195"},{"key":"9260_CR22","doi-asserted-by":"crossref","unstructured":"Mehta S, Rastegari M, Shapiro L, Hajishirzi H (2019) Espnetv2: a light-weight, power efficient, and general purpose convolutional neural network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9190\u20139200","DOI":"10.1109\/CVPR.2019.00941"},{"issue":"2","key":"9260_CR23","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/S0378-3758(00)00115-4","volume":"90","author":"H Shimodaira","year":"2000","unstructured":"Shimodaira H (2000) Improving predictive inference under covariate shift by weighting the log-likelihood function. J Stat Plan Inference 90(2):227\u2013244","journal-title":"J Stat Plan Inference"},{"key":"9260_CR24","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, pp 448\u2013456"},{"key":"9260_CR25","unstructured":"Clevert D-A, Unterthiner T, Hochreiter S (2015) Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289"},{"key":"9260_CR26","unstructured":"Raiko T, Valpola H, LeCun Y (2012) Deep learning made easier by linear transformations in perceptrons. In: Artificial intelligence and statistics, pp 924\u2013932"},{"key":"9260_CR27","unstructured":"Klambauer G, Unterthiner T, Mayr A, Hochreiter S (2017) Self-normalizing neural networks. In: Advances in neural information processing systems, vol 30"},{"key":"9260_CR28","unstructured":"Ba JL, Kiros JR, Hinton GE (2016) Layer normalization. arXiv preprint arXiv:1607.06450"},{"key":"9260_CR29","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: 2015 IEEE international conference on computer vision, pp 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"key":"9260_CR30","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th international conference on machine learning, pp 807\u2013814"},{"key":"9260_CR31","unstructured":"Le QV, Jaitly N, Hinton GE (2015) A simple way to initialize recurrent networks of rectified linear units. arXiv preprint arXiv:1504.00941"},{"key":"9260_CR32","unstructured":"Pascanu R, Mikolov T, Bengio Y (2013) On the difficulty of training recurrent neural networks. In: International conference on machine learning, pp 1310\u20131318"},{"key":"9260_CR33","unstructured":"Maas AL, Hannun AY, Ng AY (2013) Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of the 30th international conference on machine learning, vol 30, p 3"},{"key":"9260_CR34","unstructured":"Ramachandran P, Zoph B, Le QV (2017) Searching for activation functions. arXiv preprint arXiv:1710.05941"},{"key":"9260_CR35","unstructured":"Misra D (2019) Mish: A self regularized non-monotonic neural activation function. arXiv preprint arXiv:1908.08681 4(2):10\u201348550"},{"key":"9260_CR36","unstructured":"Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Proceedings of the 14th international conference on artificial intelligence and statistics, pp 315\u2013323"},{"key":"9260_CR37","doi-asserted-by":"crossref","unstructured":"Sun Y, Wang X, Tang X (2015) Deeply learned face representations are sparse, selective, and robust. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2892\u20132900","DOI":"10.1109\/CVPR.2015.7298907"},{"key":"9260_CR38","unstructured":"Xu B, Wang N, Chen T, Li M (2015) Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853"},{"key":"9260_CR39","unstructured":"Krizhevsky A, Hinton G (2010) Convolutional deep belief networks on cifar-10. Technical report, Toronto University"},{"key":"9260_CR40","unstructured":"Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the 13th international conference on artificial intelligence and statistics, pp 249\u2013256"},{"key":"9260_CR41","doi-asserted-by":"crossref","unstructured":"Luo G (2010) An efficient DSP implantation of wavelet audio coding for digital communication. In: 4th international conference on digital society, pp 66\u201371","DOI":"10.1109\/ICDS.2010.20"},{"key":"9260_CR42","doi-asserted-by":"crossref","unstructured":"Vyas A, Paik J (2018) Applications of multiscale transforms to image denoising: survey. In: 2018 international conference on electronics, information, and communication, pp 1\u20133","DOI":"10.23919\/ELINFOCOM.2018.8330574"},{"key":"9260_CR43","doi-asserted-by":"crossref","unstructured":"Cao H, Luo G (2016) Wavelet speech enhancement based on improved Teager energy operator and local variance analysis. In: Artificial intelligence science and technology, pp 541\u2013552","DOI":"10.1142\/9789813206823_0069"},{"issue":"6","key":"9260_CR44","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1109\/72.165591","volume":"3","author":"Q Zhang","year":"1992","unstructured":"Zhang Q, Benveniste A (1992) Wavelet networks. IEEE Trans Neural Netw 3(6):889\u2013898","journal-title":"IEEE Trans Neural Netw"},{"issue":"2","key":"9260_CR45","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1109\/72.557660","volume":"8","author":"Q Zhang","year":"1997","unstructured":"Zhang Q (1997) Using wavelet network in nonparametric estimation. IEEE Trans Neural Netw 8(2):227\u2013236","journal-title":"IEEE Trans Neural Netw"},{"issue":"4","key":"9260_CR46","doi-asserted-by":"publisher","first-page":"862","DOI":"10.1109\/TNN.2005.849842","volume":"16","author":"SA Billings","year":"2005","unstructured":"Billings SA, Wei H-L (2005) A new class of wavelet networks for nonlinear system identification. IEEE Trans Neural Netw 16(4):862\u2013874","journal-title":"IEEE Trans Neural Netw"},{"issue":"10","key":"9260_CR47","doi-asserted-by":"publisher","first-page":"1286","DOI":"10.1016\/j.neunet.2010.07.006","volume":"23","author":"H-L Wei","year":"2010","unstructured":"Wei H-L, Billings SA, Zhao Y, Guo L (2010) An adaptive wavelet neural network for spatio-temporal system identification. Neural Netw 23(10):1286\u20131299","journal-title":"Neural Netw"},{"key":"9260_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neunet.2013.01.008","volume":"42","author":"AK Alexandridis","year":"2013","unstructured":"Alexandridis AK, Zapranis AD (2013) Wavelet neural networks: a practical guide. Neural Netw 42:1\u201327","journal-title":"Neural Netw"},{"key":"9260_CR49","volume-title":"Introduction to wavelets and wavelet transforms: a primer","author":"C Sidney Burrus","year":"1998","unstructured":"Sidney Burrus C, Gopinath RA, Guo H (1998) Introduction to wavelets and wavelet transforms: a primer, 1st edn. Prentice Hall, New Jersey","edition":"1"},{"issue":"1","key":"9260_CR50","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1006\/acha.1993.1008","volume":"1","author":"DL Donoho","year":"1993","unstructured":"Donoho DL (1993) Unconditional bases are optimal bases for data compression and for statistical estimation. Appl Comput Harmonic Anal 1(1):100\u2013115","journal-title":"Appl Comput Harmonic Anal"},{"issue":"5","key":"9260_CR51","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1109\/18.57199","volume":"36","author":"I Daubechies","year":"1990","unstructured":"Daubechies I (1990) The wavelet transform, time-frequency localization and signal analysis. IEEE Trans Inf Theory 36(5):961\u20131005","journal-title":"IEEE Trans Inf Theory"},{"issue":"1","key":"9260_CR52","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1137\/0524017","volume":"24","author":"CK Chui","year":"1993","unstructured":"Chui CK, Shi X (1993) Inequalities of Littlewood\u2013Paley type for frames and wavelets. SIAM J Math Anal 24(1):263\u2013277","journal-title":"SIAM J Math Anal"},{"key":"9260_CR53","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1137\/1.9781611970104","volume-title":"3. Ten lectures on wavelets","author":"I Daubechies","year":"1992","unstructured":"Daubechies I (1992) 3. Ten lectures on wavelets. SIAM, Pennsylvania, pp 53\u2013105"},{"issue":"11","key":"9260_CR54","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 (1998) Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11):2278\u20132324","journal-title":"Proceedings of the IEEE"},{"key":"9260_CR55","unstructured":"Saxe AM, McClelland JL, Ganguli S (2013) Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. arXiv preprint arXiv:1312.6120"},{"issue":"4","key":"9260_CR56","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1109\/LPT.2015.2496659","volume":"28","author":"H Liu","year":"2015","unstructured":"Liu H, Wang D, Liu J, Liu S (2015) Range tunable optical fiber micro-fabry-p\u00e9rot interferometer for pressure sensing. IEEE Photonics Technol Lett 28(4):402\u2013405","journal-title":"IEEE Photonics Technol Lett"},{"key":"9260_CR57","doi-asserted-by":"crossref","unstructured":"Lin H, Luo G, Cao H, Fang X, Zhou F (2019) Complex nonlinear system modelling and parameters identification by deep neural networks. DEStech Transactions on Computer Science and Engineering (AICAE)","DOI":"10.12783\/dtcse\/aicae2019\/31445"},{"key":"9260_CR58","unstructured":"Warden P (2018) Speech commands: A dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:1804.03209"},{"key":"9260_CR59","doi-asserted-by":"crossref","unstructured":"Kim B, Chang S, Lee J, Sung D (2021) Broadcasted residual learning for efficient keyword spotting. arXiv preprint arXiv:2106.04140","DOI":"10.21437\/Interspeech.2021-383"},{"key":"9260_CR60","doi-asserted-by":"crossref","unstructured":"Majumdar S, Ginsburg B (2020) Matchboxnet: 1d time-channel separable convolutional neural network architecture for speech commands recognition. arXiv preprint arXiv:2004.08531","DOI":"10.21437\/Interspeech.2020-1058"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-09260-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-09260-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-09260-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T10:12:01Z","timestamp":1708164721000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-09260-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,22]]},"references-count":60,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["9260"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-09260-y","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2023,12,22]]},"assertion":[{"value":"29 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors certify that there is no actual or potential conflict of interest in relation to this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}