{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T04:53:42Z","timestamp":1769316822898,"version":"3.49.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030438586","type":"print"},{"value":"9783030438593","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-43859-3_6","type":"book-chapter","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T14:03:01Z","timestamp":1586440981000},"page":"80-89","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Fusion of Hilbert-Huang Transform and Deep Convolutional Neural Network for Predominant Musical Instruments Recognition"],"prefix":"10.1007","author":[{"given":"Xiaoquan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Soraghan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinchang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,4,9]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 1\u201327 (2011)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"6_CR2","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1162\/neco.1992.4.2.141","volume":"4","author":"R Battiti","year":"1992","unstructured":"Battiti, R.: First-and second-order methods for learning: between steepest descent and Newton\u2019s method. Neural Comput. 4, 141\u2013166 (1992)","journal-title":"Neural Comput."},{"key":"6_CR3","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/978-3-642-11674-2_5","volume":"274","author":"JS Downie","year":"2010","unstructured":"Downie, J.S., Ehmann, A.F., Bay, M., Jones, M.C.: The music information retrieval evaluation eXchange: some observations and insights. Stud. Comput. Intell. 274, 93\u2013115 (2010)","journal-title":"Stud. Comput. Intell."},{"issue":"3","key":"6_CR4","first-page":"18","volume":"2","author":"A Liaw","year":"2002","unstructured":"Liaw, A., Wiener, M.: Classification and regression by randomForest. R News 2(3), 18\u201322 (2002)","journal-title":"R News"},{"key":"6_CR5","doi-asserted-by":"publisher","first-page":"590","DOI":"10.14419\/ijet.v7i3.34.19388","volume":"7","author":"D Kim","year":"2018","unstructured":"Kim, D., Sung, T.T., Cho, S., Lee, G., Sohn, C.-B.: A single predominant instrument recognition of polyphonic music using CNN-based timbre analysis. Int. J. Eng. Technol. 7, 590\u2013593 (2018)","journal-title":"Int. J. Eng. Technol."},{"key":"6_CR6","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1109\/TASLP.2016.2632307","volume":"25","author":"Y Han","year":"2017","unstructured":"Han, Y., Kim, J., Lee, K., Han, Y., Kim, J., Lee, K.: Deep convolutional neural networks for predominant instrument recognition in polyphonic music. IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP) 25, 208\u2013221 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP)"},{"key":"6_CR7","volume-title":"The Physics of Musical Instruments","author":"NH Fletcher","year":"2012","unstructured":"Fletcher, N.H., Rossing, T.D.: The Physics of Musical Instruments. Springer, Heidelberg (2012)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"McAdams, S., Giordano, B.L.: The perception of musical timbre. In: The Oxford Handbook of Music Psychology, pp. 113\u2013123 (2016)","DOI":"10.1093\/oxfordhb\/9780198722946.013.12"},{"key":"6_CR9","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1007\/s10844-015-0360-9","volume":"46","author":"D Bhalke","year":"2016","unstructured":"Bhalke, D., Rao, C.R., Bormane, D.S.: Automatic musical instrument classification using fractional fourier transform based-MFCC features and counter propagation neural network. J. Intell. Inf. Syst. 46, 425\u2013446 (2016)","journal-title":"J. Intell. Inf. Syst."},{"key":"6_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1007\/978-3-319-94211-7_19","volume-title":"Image and Signal Processing","author":"A Banerjee","year":"2018","unstructured":"Banerjee, A., Ghosh, A., Palit, S., Ballester, M.A.F.: A novel approach to string instrument recognition. In: Mansouri, A., El Moataz, A., Nouboud, F., Mammass, D. (eds.) ICISP 2018. LNCS, vol. 10884, pp. 165\u2013175. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-94211-7_19"},{"key":"6_CR11","unstructured":"Slizovskaia, O., G\u00f3mez, E., Haro, G.: Automatic musical instrument recognition in audiovisual recordings by combining image and audio classification strategies. In: SMC 2016 \u2013 13th Sound and Music Computing Conference, Proceedings, pp. 442\u2013447 (2016)"},{"key":"6_CR12","unstructured":"Bosch, J.J., Janer, J., Fuhrmann, F., Herrera, P.: A comparison of sound segregation techniques for predominant instrument recognition in musical audio signals. In: ISMIR, pp. 559\u2013564 (2012)"},{"key":"6_CR13","unstructured":"Li, P., Qian, J., Wang, T.: Automatic instrument recognition in polyphonic music using convolutional neural networks. arXiv preprint: arXiv:1511.05520 (2015)"},{"key":"6_CR14","unstructured":"Bittner, R.M., Salamon, J., Tierney, M., Mauch, M., Cannam, C., Bello, J.P.: MedleyDB: a multitrack dataset for annotation-intensive mir research. In: ISMIR, pp. 155\u2013160 (2014)"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Hung, Y.N., Chen, Y.A., Yang, Y.H.: Multitask learning for frame-level instrument recognition. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 381\u2013385 (2019)","DOI":"10.1109\/ICASSP.2019.8683426"},{"key":"6_CR16","unstructured":"Gururani, S., Sharma, M., Lerch, A.: An Attention Mechanism for Musical Instrument Recognition. arXiv preprint: arXiv:1907.04294 (2019)"},{"key":"6_CR17","unstructured":"Humphrey, E., Durand, S., McFee, B.: OpenMIC-2018: an open data-set for multiple instrument recognition. In: ISMIR, pp. 438\u2013444 (2018)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Sandoval, S., De Leon, P.L., Liss, J.M.: Hilbert spectral analysis of vowels using intrinsic mode functions. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 569\u2013575. IEEE (2015)","DOI":"10.1109\/ASRU.2015.7404846"},{"key":"6_CR19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21945-5","volume-title":"Fundamentals of Music Processing: Audio, Analysis, Algorithms","author":"M M\u00fcller","year":"2015","unstructured":"M\u00fcller, M.: Fundamentals of Music Processing: Audio, Analysis, Algorithms. Applications. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-21945-5"},{"key":"6_CR20","doi-asserted-by":"publisher","DOI":"10.1002\/9781118393550","volume-title":"An Introduction to Audio Content Analysis: Applications in Signal Processing and Music Informatics","author":"A Lerch","year":"2012","unstructured":"Lerch, A.: An Introduction to Audio Content Analysis: Applications in Signal Processing and Music Informatics. Wiley-IEEE Press, Hoboken (2012)"},{"key":"6_CR21","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1080\/00423110802167466","volume":"47","author":"A Ayenu-Prah","year":"2009","unstructured":"Ayenu-Prah, A., Attoh-Okine, N.: Comparative study of Hilbert-Huang transform, Fourier transform and wavelet transform in pavement profile analysis. Veh. Syst. Dyn. 47, 437\u2013456 (2009)","journal-title":"Veh. Syst. Dyn."},{"key":"6_CR22","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings (2014)"},{"key":"6_CR23","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1007\/s12559-017-9529-6","volume":"10","author":"Y Yan","year":"2018","unstructured":"Yan, Y., et al.: Cognitive fusion of thermal and visible imagery for effective detection and tracking of pedestrians in videos. Cogn. Comput. 10, 94\u2013104 (2018)","journal-title":"Cogn. Comput."},{"key":"6_CR24","unstructured":"Peeters, G.: A large set of audio features for sound description (similarity and classification). CUIDADO project IRCAM technical report (2004)"},{"key":"6_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2015.11.044","volume":"185","author":"J Zabalza","year":"2016","unstructured":"Zabalza, J., et al.: Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging. Neurocomputing 185, 1\u201310 (2016)","journal-title":"Neurocomputing"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR27","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.knosys.2017.10.018","volume":"139","author":"G Sun","year":"2018","unstructured":"Sun, G., Ma, P., Ren, J., Zhang, A., Jia, X.: A stability constrained adaptive alpha for gravitational search algorithm. Knowl.-Based Syst. 139, 200\u2013213 (2018)","journal-title":"Knowl.-Based Syst."}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Music, Sound, Art and Design"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-43859-3_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,20]],"date-time":"2022-10-20T23:14:04Z","timestamp":1666307644000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-43859-3_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030438586","9783030438593"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-43859-3_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"9 April 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EvoMUSART","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Intelligence in Music, Sound, Art and Design (Part of EvoStar)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Seville","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 April 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 April 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"evomusart2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.evostar.org\/2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"15","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"48% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}