{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T19:20:13Z","timestamp":1770492013292,"version":"3.49.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1007\/s11265-021-01661-3","type":"journal-article","created":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T19:02:45Z","timestamp":1617303765000},"page":"977-987","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["PureMIC: A New Audio Dataset for the Classification of Musical Instruments based on Convolutional Neural Networks"],"prefix":"10.1007","volume":"93","author":[{"given":"Gon\u00e7alo","family":"Castel-Branco","sequence":"first","affiliation":[]},{"given":"Gabriel","family":"Falcao","sequence":"additional","affiliation":[]},{"given":"Fernando","family":"Perdig\u00e3o","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,4,1]]},"reference":[{"key":"1661_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21945-5","volume-title":"Fundamentals of music processing","author":"M M\u00fcller","year":"2015","unstructured":"M\u00fcller, M. (2015). Fundamentals of music processing. Berlin: Springer."},{"key":"1661_CR2","doi-asserted-by":"crossref","unstructured":"Mcadams, S. (1993). Recognition of sound sources and events. In Thinking in sound: the cognitive psychology of human audition (pp. 146\u2013198): Oxford University Press.","DOI":"10.1093\/acprof:oso\/9780198522577.003.0006"},{"key":"1661_CR3","unstructured":"Takahashi, T., Fukayama, S., & Goto, M. (2018). Instrudive: A music visualization system based on automatically recognized instrumentation."},{"issue":"1","key":"1661_CR4","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1076\/jnmr.32.1.3.16798","volume":"32","author":"P Herrera-Boyer","year":"2003","unstructured":"Herrera-Boyer, P, Peeters, G., & Dubnov, S. (2003). Automatic classification of musical instrument sounds. Journal of New Music Research, 32(1), 3\u201321.","journal-title":"Journal of New Music Research"},{"key":"1661_CR5","doi-asserted-by":"crossref","unstructured":"Lostanlen, V., And\u00e9n, J., & Lagrang\u00e9, M. (2018). Extended playing techniques: The next milestone in musical instrument recognition. arXiv:1808.09730v1.","DOI":"10.1145\/3273024.3273036"},{"key":"1661_CR6","doi-asserted-by":"crossref","unstructured":"Kumar, A., & Raj, B. (2016). Audio event detection using weakly labeled data. In Proc. of the ACM Multimedia Conference (MM 2016), pp 1038\u20131047, Association for Computing Machinery, Inc.","DOI":"10.1145\/2964284.2964310"},{"key":"1661_CR7","doi-asserted-by":"crossref","unstructured":"Kong, Q., Xu, Y., Wang, W., & Plumbley, M.D. (2017). A joint detection-classification model for audio tagging of weakly labelled data. In Proc. of the IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 641\u2013645, IEEE.","DOI":"10.1109\/ICASSP.2017.7952234"},{"key":"1661_CR8","doi-asserted-by":"crossref","unstructured":"Giannoulis, D., Benetos, E., Stowell, D., Rossignol, M., Lagrange, M., & Plumbley, M.D. (2013). Detection and classification of acoustic scenes and events: An IEEE AASP challenge. In IEEE workshop on applications of signal processing to audio and acoustics (pp. 1\u20134).","DOI":"10.1109\/WASPAA.2013.6701819"},{"key":"1661_CR9","unstructured":"Detection and Classification of Acoustic Scenes and Events: Outcome of the DCASE 2016 Challenge,\u201d Tech. Rep. 2, 2018."},{"key":"1661_CR10","unstructured":"Mesaros, A., Heittola, T., Diment, A., Elizalde, B., Shah, A., Vincent, E., Raj, B., & Virtanen, T. (2017). DCASE 2017 Challenge setup: tasks, datasets and baseline system."},{"key":"1661_CR11","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., Ellis, D.P.W., Freedman, D., Jansen, A., Lawrence, W., Moore, R.C., Plakal, M., & Ritter, M. (2017). Audio Set: An ontology and human-labeled dataset for audio events. In Proc. of IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 776\u2013780).","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"1661_CR12","doi-asserted-by":"crossref","unstructured":"Hershey, S., Chaudhuri, S., Ellis, D.P.W., Gemmeke, JF., Jansen, A., Channing Moore, R., Plakal, M., Platt, D., Saurous, R.A., Seybold, B., Slaney, M., Weiss, R.J., & Wilson, K. (2017). CNN architectures for large-scale audio classification. In Proc. of IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 131\u2013135).","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"1661_CR13","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition, arXiv:1409.1556v6."},{"key":"1661_CR14","doi-asserted-by":"crossref","unstructured":"Bro, R. (2014). Analytical methods principal component analysis. Royal Society Of Chemistry 2812\u20132831.","DOI":"10.1039\/C3AY41907J"},{"key":"1661_CR15","unstructured":"Humphrey, E.J., Durand, S., & Mcfee, B. (2018). OpenMIC-2018: An open dataset for multiple instrument recognition. In Proc. of the 19th international society for music information retrieval conference (ISMIR)."},{"key":"1661_CR16","unstructured":"Defferrard, M., Benzi, K., Vandergheynst, P., & Bresson, X. (2016). FMA: A dataset for music analysis. 316\u2013323."},{"key":"1661_CR17","unstructured":"Bandiera, G., Picas, O.R., & Serra, X. (2016). Good-sounds.org: a framework to explore goodness in instrumental sounds. In Proc. of the 17th international society for music information retrieval conference (ISMIR)."},{"key":"1661_CR18","unstructured":"Engel, J., Resnick, C., Roberts, A., Dieleman, S., Norouzi, M., Eck, D., & Simonyan, K. (2017). Neural audio synthesis of musical notes with wavenet autoencoders, Tech. Rep."},{"key":"1661_CR19","unstructured":"Thickstun, J., Harchaoui, Z., & Kakade, S. (2016). Learning features of music from scratch. In 5th International conference on learning representations, ICLR 2017 - conference track proceedings."},{"key":"1661_CR20","unstructured":"Bittner, R., Salamon, J., Tierney, M., Mauch, M., Cannam, C., & Bello, J. (2014). MedleyDB: A multitrack dataset for annotation-intensive MIR research."},{"key":"1661_CR21","unstructured":"Irmas. (2020). IRMAS: A dataset for instrument recognition in musical audio signals - MTG - Music Technology Group (UPF), [online]. https:\/\/www.upf.edu\/web\/mtg\/irmas, [Accessed Oct 2020."},{"key":"1661_CR22","doi-asserted-by":"crossref","unstructured":"Castel-Branco, G., Falcao, G., & Perdig\u00e3o, F. (2020). Enhancing the labelling of audio samples for automatic instrument classification based on neural networks. In Proc. of IEEE international conference on acoustics, speech, and signal processing (ICASSP).","DOI":"10.1109\/ICASSP40776.2020.9053625"},{"key":"1661_CR23","unstructured":"Nair, V., & Hinton, G.E. (2010). Rectified linear units improve restricted boltzmann machines. In Proc. of the 27th international conference on machine learning (ICML), pp 807\u2013814."},{"key":"1661_CR24","unstructured":"Ruder, S. (2017). An overview of gradient descent optimization algorithms, Tech. Rep."},{"key":"1661_CR25","unstructured":"NVIDIA. (2020). The NVIDIA CUDA Deep Neural Network library (cuDNN), [online]. https:\/\/developer.nvidia.com\/cudnn, [accessed Jun 2020]."},{"issue":"4","key":"1661_CR26","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1109\/MSP.2012.2192212","volume":"29","author":"G Falcao","year":"2012","unstructured":"Falcao, G., Silva, V., Sousa, L., & Andrade, J. (2012). Portable LDPC decoding on multicores using openCL. IEEE Signal Processing Magazine, 29(4), 81\u2013109.","journal-title":"IEEE Signal Processing Magazine"},{"key":"1661_CR27","unstructured":"KERAS. (2020). Keras GitHub repository, [online]. https:\/\/github.com\/keras-team\/keras, [accessed Oct 2020."},{"key":"1661_CR28","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z. , Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., & et al. (2016). Tensorflow: A system for large-scale machine learning. In 12th Symposium on Operating Systems Design and Implementation. pp. 265\u2013283."},{"issue":"6","key":"1661_CR29","doi-asserted-by":"publisher","first-page":"162","DOI":"10.3390\/app6060162","volume":"6","author":"A Mesaros","year":"2016","unstructured":"Mesaros, A., Heittola, T., & Virtanen, T. (2016). Metrics for polyphonic sound event detection. Applied Sciences (Switzerland), 6(6), 162.","journal-title":"Applied Sciences (Switzerland)"},{"issue":"85","key":"1661_CR30","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, \u00c9. (2011). Scikit-learn: machine learning in python. Journal of Machine Learning Research, 12(85), 2825\u20132830.","journal-title":"Journal of Machine Learning Research"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-021-01661-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11265-021-01661-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-021-01661-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T22:00:23Z","timestamp":1630706423000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11265-021-01661-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,1]]},"references-count":30,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["1661"],"URL":"https:\/\/doi.org\/10.1007\/s11265-021-01661-3","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,1]]},"assertion":[{"value":"24 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 November 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}