{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:31:02Z","timestamp":1761060662235,"version":"3.37.3"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2018,9,24]],"date-time":"2018-09-24T00:00:00Z","timestamp":1537747200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001821","name":"Vienna Science and Technology Fund","doi-asserted-by":"crossref","award":["MA14-018"],"award-info":[{"award-number":["MA14-018"]}],"id":[{"id":"10.13039\/501100001821","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2020,2]]},"DOI":"10.1007\/s00521-018-3704-x","type":"journal-article","created":{"date-parts":[[2018,9,24]],"date-time":"2018-09-24T15:54:01Z","timestamp":1537804441000},"page":"941-954","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Basic filters for convolutional neural networks applied to music: Training or design?"],"prefix":"10.1007","volume":"32","author":[{"given":"Monika","family":"D\u00f6rfler","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0962-6224","authenticated-orcid":false,"given":"Thomas","family":"Grill","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roswitha","family":"Bammer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arthur","family":"Flexer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,24]]},"reference":[{"issue":"12","key":"3704_CR1","doi-asserted-by":"publisher","first-page":"7770","DOI":"10.1109\/TIT.2017.2718963","volume":"63","author":"LD Abreu","year":"2017","unstructured":"Abreu LD, Romero JL (2017) MSE estimates for multitaper spectral estimation and off-grid compressive sensing. IEEE Trans Inf Theory 63(12):7770\u20137776","journal-title":"IEEE Trans Inf Theory"},{"issue":"16","key":"3704_CR2","doi-asserted-by":"publisher","first-page":"4114","DOI":"10.1109\/TSP.2014.2326991","volume":"62","author":"J And\u00e9n","year":"2014","unstructured":"And\u00e9n J, Mallat S (2014) Deep scattering spectrum. IEEE Trans Signal Process 62(16):4114\u20134128","journal-title":"IEEE Trans Signal Process"},{"unstructured":"Anselmi F, Leibo JZ, Rosasco L, Mutch J, Tacchetti A, Poggio TA (2013) Unsupervised learning of invariant representations in hierarchical architectures. CoRR arxiv:1311.4158","key":"3704_CR3"},{"issue":"6","key":"3704_CR4","doi-asserted-by":"publisher","first-page":"1481","DOI":"10.1016\/j.cam.2011.09.011","volume":"236","author":"P Balazs","year":"2011","unstructured":"Balazs P, D\u00f6rfler M, Jaillet F, Holighaus N, Velasco G (2011) Theory, implementation and applications of nonstationary gabor frames. J Comput Appl Math 236(6):1481\u20131496","journal-title":"J Comput Appl Math"},{"issue":"6","key":"3704_CR5","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MSP.2013.2266075","volume":"30","author":"P Balazs","year":"2013","unstructured":"Balazs P, D\u00f6rfler M, Kowalski M, Torr\u00e9sani B (2013) Adapted and adaptive linear time-frequency representations: a synthesis point of view. IEEE Signal Process Mag 30(6):20\u201331","journal-title":"IEEE Signal Process Mag"},{"doi-asserted-by":"crossref","unstructured":"Bammer R, D\u00f6rfler M (2017) Invariance and stability of Gabor scattering for music signals. In: Sampling theory and applications (SampTA), 2017 international conference on. IEEE, pp 299\u2013302","key":"3704_CR6","DOI":"10.1109\/SAMPTA.2017.8024444"},{"unstructured":"Boulanger-Lewandowski N, Bengio Y, Vincent P (2012) Modeling temporal dependencies in high-dimensional sequences: application to polyphonic music generation and transcription. arXiv preprint arXiv:1206.6392","key":"3704_CR7"},{"issue":"2","key":"3704_CR8","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1109\/TETCI.2017.2771298","volume":"2","author":"K Choi","year":"2018","unstructured":"Choi K, Fazekas G, Sandler M, Cho K (2018) The effects of noisy labels on deep convolutional neural networks for music tagging. IEEE Trans Emerg Top Comput Intell 2(2):139\u2013149","journal-title":"IEEE Trans Emerg Top Comput Intell"},{"unstructured":"Choi K, Fazekas G, Sandler M (2016) Automatic tagging using deep convolutional neural networks. In: Proceddings of the 17th international society for music information retrieval conference","key":"3704_CR9"},{"doi-asserted-by":"crossref","unstructured":"Chuan CH, Herremans D (2018) Modeling temporal tonal relations in polyphonic music through deep networks with a novel image-based representation. In: Thirty-second AAAI conference on artificial intelligence","key":"3704_CR10","DOI":"10.1609\/aaai.v32i1.11880"},{"unstructured":"Dieleman S, Brakel P, Schrauwen B (2011) Audio-based music classification with a pretrained convolutional network. In: 12th international society for music information retrieval conference (ISMIR-2011). University of Miami, pp 669\u2013674","key":"3704_CR11"},{"doi-asserted-by":"publisher","unstructured":"Dieleman S, Schrauwen B (2014) End-to-end learning for music audio. In: Acoustics, speech and signal processing (ICASSP), 2014 IEEE international conference on, pp 6964\u20136968. https:\/\/doi.org\/10.1109\/ICASSP.2014.6854950","key":"3704_CR12","DOI":"10.1109\/ICASSP.2014.6854950"},{"issue":"1","key":"3704_CR13","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1076\/jnmr.30.1.3.7124","volume":"30","author":"M D\u00f6rfler","year":"2001","unstructured":"D\u00f6rfler M (2001) Time-frequency analysis for music signals: a mathematical approach. J New Music Res 30(1):3\u201312","journal-title":"J New Music Res"},{"doi-asserted-by":"crossref","unstructured":"D\u00f6rfler M, Bammer R, Grill T (2017) Inside the spectrogram: convolutional neural networks in audio processing. In: International conference on sampling theory and applications (SampTA). IEEE, pp 152\u2013155","key":"3704_CR14","DOI":"10.1109\/SAMPTA.2017.8024472"},{"issue":"2","key":"3704_CR15","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s00041-009-9085-x","volume":"16","author":"M D\u00f6rfler","year":"2010","unstructured":"D\u00f6rfler M, Torr\u00e9sani B (2010) Representation of operators in the time-frequency domain and generalized Gabor multipliers. J Fourier Anal Appl 16(2):261\u2013293","journal-title":"J Fourier Anal Appl"},{"key":"3704_CR16","first-page":"233","volume-title":"Gabor analysis and algorithms, applied and numerical harmonic analysis","author":"HG Feichtinger","year":"1998","unstructured":"Feichtinger HG, Kozek W (1998) Quantization of TF lattice-invariant operators on elementary LCA groups. In: Feichtinger HG, Strohmer T (eds) Gabor analysis and algorithms, applied and numerical harmonic analysis. Birkh\u00e4user, Boston, pp 233\u2013266"},{"key":"3704_CR17","first-page":"99","volume-title":"Advances in Gabor analysis, applied and numerical harmonic analysis","author":"HG Feichtinger","year":"2003","unstructured":"Feichtinger HG, Nowak K (2003) A first survey of Gabor multipliers. In: Feichtinger HG, Strohmer T (eds) Advances in Gabor analysis, applied and numerical harmonic analysis. Birkh\u00e4user, Boston, pp 99\u2013128"},{"key":"3704_CR18","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press, Cambridge"},{"unstructured":"Grill T, Schl\u00fcter J (2015) Music boundary detection using neural networks on combined features and two-level annotations. In: Proceedings of the 16th international society for music information retrieval conference (ISMIR 2015). Malaga, Spain, pp 531\u2013537","key":"3704_CR19"},{"doi-asserted-by":"crossref","unstructured":"Grohs P, Wiatowski T, B\u00f6lcskei H (2016) Deep convolutional neural networks on cartoon functions. In: Information theory (ISIT), 2016 IEEE international symposium on. IEEE, pp 1163\u20131167","key":"3704_CR20","DOI":"10.1109\/ISIT.2016.7541482"},{"issue":"4","key":"3704_CR21","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1109\/TASL.2012.2234114","volume":"21","author":"N Holighaus","year":"2013","unstructured":"Holighaus N, D\u00f6rfler M, Velasco GA, Grill T (2013) A framework for invertible, real-time constant-Q transforms. IEEE Trans Audio Speech Lang Process 21(4):775\u2013785","journal-title":"IEEE Trans Audio Speech Lang Process"},{"unstructured":"Humphrey EJ, Bello JP (2012) Rethinking automatic chord recognition with convolutional neural networks. In: Machine learning and applications (ICMLA), 2012 11th international conference on. IEEE, vol 2, pp 357\u2013362","key":"3704_CR22"},{"unstructured":"Humphrey EJ, Montecchio N, Bittner R, Jansson A, Jehan T (2017) Mining labeled data from web-scale collections for vocal activity detection in music. In: Proceedings of the 18th international society for music information retrieval conference (ISMIR), Suzhou, China","key":"3704_CR23"},{"unstructured":"Kingma D, Ba J (2015) Adam: a method for stochastic optimization. In: Proceedings of the 6th international conference on learning representations (ICLR). San Diego, USA","key":"3704_CR24"},{"doi-asserted-by":"crossref","unstructured":"Korzeniowski F, Widmer G (2016) A fully convolutional deep auditory model for musical chord recognition. In: Machine learning for signal processing (MLSP), 2016 IEEE 26th international workshop on. IEEE, pp 1\u20136","key":"3704_CR25","DOI":"10.1109\/MLSP.2016.7738895"},{"issue":"11","key":"3704_CR26","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. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"unstructured":"Lee H, Pham P, Largman Y, Ng AY (2009) Unsupervised feature learning for audio classification using convolutional deep belief networks. In: Advances in neural information processing systems, pp 1096\u20131104","key":"3704_CR27"},{"doi-asserted-by":"crossref","unstructured":"Leglaive S, Hennequin R, Badeau R (2015) Singing voice detection with deep recurrent neural networks. In: Acoustics, speech and signal processing (ICASSP), 2015 IEEE international conference on. IEEE, pp 121\u2013125","key":"3704_CR28","DOI":"10.1109\/ICASSP.2015.7177944"},{"issue":"8","key":"3704_CR29","doi-asserted-by":"publisher","first-page":"1369","DOI":"10.1109\/TASLP.2018.2825108","volume":"26","author":"B Lehner","year":"2018","unstructured":"Lehner B, Schl\u00fcter J, Widmer G (2018) Online, loudness-invariant vocal detection in mixed music signals. IEEE\/ACM Trans Audio Speech Lang Process 26(8):1369\u20131380","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"unstructured":"Malik M, Adavanne S, Drossos K, Virtanen T, Ticha D, Jarina R (2017) Stacked convolutional and recurrent neural networks for music emotion recognition. arXiv preprint arXiv:1706.02292","key":"3704_CR30"},{"issue":"10","key":"3704_CR31","doi-asserted-by":"publisher","first-page":"1331","DOI":"10.1002\/cpa.21413","volume":"65","author":"S Mallat","year":"2012","unstructured":"Mallat S (2012) Group invariant scattering. Commun Pure Appl Math 65(10):1331\u20131398","journal-title":"Commun Pure Appl Math"},{"issue":"2065","key":"3704_CR32","doi-asserted-by":"publisher","first-page":"20150203","DOI":"10.1098\/rsta.2015.0203","volume":"374","author":"St\u00e9phane Mallat","year":"2016","unstructured":"Mallat S (2016) Understanding deep convolutional networks. Philos Trans R Soc Lond A Math Phys Eng Sci 374(2065). https:\/\/doi.org\/10.1098\/rsta.2015.0203 . URL\u00a0 http:\/\/rsta.royalsocietypublishing.org\/content\/374\/2065\/20150203","journal-title":"Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences"},{"doi-asserted-by":"crossref","unstructured":"Schl\u00fcter J, B\u00f6ck S (2013) Musical onset detection with convolutional neural networks. In: 6th international workshop on machine learning and music (MML), Prague, Czech Republic","key":"3704_CR33","DOI":"10.1109\/ICASSP.2014.6854953"},{"doi-asserted-by":"crossref","unstructured":"Schl\u00fcter J, B\u00f6ck S (2014) Improved musical onset detection with convolutional neural networks. In: Proceedings of the IEEE international conference on acoustics, speech, and signal processing (ICASSP 2014). Florence, Italy","key":"3704_CR34","DOI":"10.1109\/ICASSP.2014.6854953"},{"unstructured":"Schl\u00fcter J, Grill T (2015) Exploring data augmentation for improved singing voice detection with neural networks. In: Proceedings of the 16th international society for music information retrieval conference (ISMIR 2015). Malaga, Spain","key":"3704_CR35"},{"unstructured":"Ullrich K, Schl\u00fcter J, Grill T (2014) Boundary detection in music structure analysis using convolutional neural networks. In: Proceedings of the 15th international society for music information retrieval conference (ISMIR 2014). Taipei, Taiwan","key":"3704_CR36"},{"unstructured":"Waldspurger I (2015) Wavelet transform modulus: phase retrieval and scattering. Ph.D. thesis, Ecole normale sup\u00e9rieure-ENS PARIS","key":"3704_CR37"},{"doi-asserted-by":"publisher","unstructured":"Waldspurger I (2017) Exponential decay of scattering coefficients. In: 2017 international conference on sampling theory and applications (SampTA), pp 143\u2013146. https:\/\/doi.org\/10.1109\/SAMPTA.2017.8024473","key":"3704_CR38","DOI":"10.1109\/SAMPTA.2017.8024473"},{"unstructured":"Wiatowski T, Grohs P, B\u00f6lcskei H (2017) Energy propagation in deep convolutional neural networks. arXiv preprint arXiv:1704.03636","key":"3704_CR39"},{"unstructured":"Wiatowski T, Tschannen M, Stanic A, Grohs P, B\u00f6lcskei H (2016) Discrete deep feature extraction: a theory and new architectures. In: Proceedings of the international conference on machine learning, pp 2149\u20132158","key":"3704_CR40"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-018-3704-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00521-018-3704-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-018-3704-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,2]],"date-time":"2022-09-02T16:03:47Z","timestamp":1662134627000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00521-018-3704-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,24]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,2]]}},"alternative-id":["3704"],"URL":"https:\/\/doi.org\/10.1007\/s00521-018-3704-x","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2018,9,24]]},"assertion":[{"value":"1 December 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 September 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 September 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}