{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T10:42:00Z","timestamp":1743072120350,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819916443"},{"type":"electronic","value":"9789819916450"}],"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\/978-981-99-1645-0_4","type":"book-chapter","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T17:03:13Z","timestamp":1681405393000},"page":"39-51","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial Neural Networks for\u00a0Downbeat Estimation and\u00a0Varying Tempo Induction in\u00a0Music Signals"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6309-6116","authenticated-orcid":false,"given":"Sarah","family":"Nadi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1142-4496","authenticated-orcid":false,"given":"Jianguo","family":"Yao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,14]]},"reference":[{"issue":"1","key":"4_CR1","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MSP.2018.2869928","volume":"36","author":"E Benetos","year":"2018","unstructured":"Benetos, E., Dixon, S., Duan, Z., Ewert, S.: Automatic music transcription: an overview. IEEE Signal Process. Mag. 36(1), 20\u201330 (2018)","journal-title":"IEEE Signal Process. Mag."},{"key":"4_CR2","unstructured":"B\u00f6ck, S., Davies, M.E.: Deconstruct, analyse, reconstruct: how to improve tempo, beat, and downbeat estimation. In: Proceedings of the 21st International Society for Music Information Retrieval Conference (ISMIR), Montreal, QC, Canada, pp. 12\u201316 (2020)"},{"key":"4_CR3","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.1109\/LSP.2021.3084504","volume":"28","author":"CY Chiu","year":"2021","unstructured":"Chiu, C.Y., Su, A.W.Y., Yang, Y.H.: Drum-aware ensemble architecture for improved joint musical beat and downbeat tracking. IEEE Signal Process. Lett. 28, 1100\u20131104 (2021)","journal-title":"IEEE Signal Process. Lett."},{"issue":"12","key":"4_CR4","doi-asserted-by":"publisher","first-page":"2218","DOI":"10.1109\/TASLP.2016.2598305","volume":"24","author":"A Cogliati","year":"2016","unstructured":"Cogliati, A., Duan, Z., Wohlberg, B.: Context-dependent piano music transcription with convolutional sparse coding. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(12), 2218\u20132230 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"4_CR5","unstructured":"Davies, M.E., Degara, N., Plumbley, M.D.: Evaluation methods for musical audio beat tracking algorithms. Queen Mary University of London, Centre for Digital Music, Technical report C4DM-TR-09-06 (2009)"},{"key":"4_CR6","unstructured":"Davies, M.E., Plumbley, M.D.: A spectral difference approach to downbeat extraction in musical audio. In: 2006 14th European Signal Processing Conference, pp. 1\u20134. IEEE (2006)"},{"issue":"1","key":"4_CR7","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1017\/S026114301000067X","volume":"30","author":"T De Clercq","year":"2011","unstructured":"De Clercq, T., Temperley, D.: A corpus analysis of rock harmony. Pop. Music 30(1), 47\u201370 (2011)","journal-title":"Pop. Music"},{"key":"4_CR8","unstructured":"Di Giorgi, B., Mauch, M., Levy, M.: Downbeat tracking with tempo-invariant convolutional neural networks. arXiv preprint arXiv:2102.02282 (2021)"},{"key":"4_CR9","unstructured":"Di Giorgi, B., Zanoni, M., Sarti, A., Tubaro, S.: Automatic chord recognition based on the probabilistic modeling of diatonic modal harmony. In: nDS\u201913; Proceedings of the 8th International Workshop on Multidimensional Systems, pp. 1\u20136. VDE (2013)"},{"issue":"5","key":"4_CR10","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1109\/TSP.2003.810293","volume":"51","author":"L Durak","year":"2003","unstructured":"Durak, L., Arikan, O.: Short-time fourier transform: two fundamental properties and an optimal implementation. IEEE Trans. Signal Process. 51(5), 1231\u20131242 (2003)","journal-title":"IEEE Trans. Signal Process."},{"issue":"1","key":"4_CR11","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1109\/TASLP.2016.2623565","volume":"25","author":"S Durand","year":"2016","unstructured":"Durand, S., Bello, J.P., David, B., Richard, G.: Robust downbeat tracking using an ensemble of convolutional networks. IEEE\/ACM Trans. Audio Speech Lang. Process. 25(1), 76\u201389 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Durand, S., David, B., Richard, G.: Enhancing downbeat detection when facing different music styles. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3132\u20133136. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854177"},{"key":"4_CR13","unstructured":"Fuentes, M., McFee, B., Crayencour, H., Essid, S., Bello, J.: Analysis of common design choices in deep learning systems for downbeat tracking. In: The 19th International Society for Music Information Retrieval Conference (2018)"},{"key":"4_CR14","unstructured":"Goto, M., Hashiguchi, H., Nishimura, T., Oka, R.: Rwc music database: popular, classical and jazz music databases. In: Ismir, vol. 2, pp. 287\u2013288 (2002)"},{"issue":"5","key":"4_CR15","doi-asserted-by":"publisher","first-page":"1832","DOI":"10.1109\/TSA.2005.858509","volume":"14","author":"F Gouyon","year":"2006","unstructured":"Gouyon, F., Klapuri, A., Dixon, S., Alonso, M., Tzanetakis, G., Uhle, C., Cano, P.: An experimental comparison of audio tempo induction algorithms. IEEE Trans. Audio Speech Lang. Process. 14(5), 1832\u20131844 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"15","key":"4_CR16","first-page":"1","volume":"2004","author":"SW Hainsworth","year":"2004","unstructured":"Hainsworth, S.W., Macleod, M.D.: Particle filtering applied to musical tempo tracking. EURASIP J. Adv. Sig. Process. 2004(15), 1\u201311 (2004)","journal-title":"EURASIP J. Adv. Sig. Process."},{"key":"4_CR17","unstructured":"Hockman, J., Davies, M.E., Fujinaga, I.: One in the jungle: Downbeat detection in hardcore, jungle, and drum and bass. In: ISMIR, pp. 169\u2013174 (2012)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Holzapfel, A., Stylianou, Y.: Rhythmic similarity of music based on dynamic periodicity warping. In: 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2217\u20132220. IEEE (2008)","DOI":"10.1109\/ICASSP.2008.4518085"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Y.S., Yang, Y.H.: Pop music transformer: Beat-based modeling and generation of expressive pop piano compositions. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1180\u20131188 (2020)","DOI":"10.1145\/3394171.3413671"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Jehan, T.: Downbeat prediction by listening and learning. In: IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2005, pp. 267\u2013270. IEEE (2005)","DOI":"10.1109\/ASPAA.2005.1540221"},{"key":"4_CR21","unstructured":"Krebs, F., B\u00f6ck, S., Widmer, G.: Rhythmic pattern modeling for beat and downbeat tracking in musical audio. In: Ismir, pp. 227\u2013232. Citeseer (2013)"},{"key":"4_CR22","unstructured":"Krebs, F., B\u00f6ck, S., Widmer, G.: An efficient state-space model for joint tempo and meter tracking. In: ISMIR, pp. 72\u201378 (2015)"},{"key":"4_CR23","unstructured":"Lidy, T., Rauber, A.: Evaluation of feature extractors and psycho-acoustic transformations for music genre classification. In: ISMIR, pp. 34\u201341 (2005)"},{"key":"4_CR24","unstructured":"Livshin, A., Rodex, X.: The importance of cross database evaluation in sound classification. In: ISMIR 2003, p. 1 (2003)"},{"key":"4_CR25","unstructured":"Logan, B.: Music recommendation from song sets. In: ISMIR, pp. 425\u2013428 (2004)"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Moritz, M., Heard, M., Kim, H.W., Lee, Y.S.: Invariance of edit-distance to tempo in rhythm similarity. Psychology of Music p. 0305735620971030 (2020)","DOI":"10.1177\/0305735620971030"},{"issue":"1","key":"4_CR27","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1109\/TASL.2010.2045236","volume":"19","author":"H Papadopoulos","year":"2010","unstructured":"Papadopoulos, H., Peeters, G.: Joint estimation of chords and downbeats from an audio signal. IEEE Trans. Audio Speech Lang. Process. 19(1), 138\u2013152 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"4_CR28","unstructured":"Park, J., Choi, K., Jeon, S., Kim, D., Park, J.: A bi-directional transformer for musical chord recognition. arXiv preprint arXiv:1907.02698 (2019)"},{"issue":"6","key":"4_CR29","doi-asserted-by":"publisher","first-page":"1754","DOI":"10.1109\/TASL.2010.2098869","volume":"19","author":"G Peeters","year":"2010","unstructured":"Peeters, G., Papadopoulos, H.: Simultaneous beat and downbeat-tracking using a probabilistic framework: theory and large-scale evaluation. IEEE Trans. Audio Speech Lang. Process. 19(6), 1754\u20131769 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"2","key":"4_CR30","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"LR Rabiner","year":"1989","unstructured":"Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257\u2013286 (1989)","journal-title":"Proc. IEEE"},{"key":"4_CR31","doi-asserted-by":"publisher","first-page":"44","DOI":"10.3389\/fams.2019.00044","volume":"5","author":"M Schedl","year":"2019","unstructured":"Schedl, M.: Deep learning in music recommendation systems. Frontiers in Applied Mathematics and Statistics 5, 44 (2019)","journal-title":"Frontiers in Applied Mathematics and Statistics"},{"key":"4_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2008\/846135","volume":"2008","author":"B Schuller","year":"2008","unstructured":"Schuller, B., Eyben, F., Rigoll, G.: Tango or waltz?: putting ballroom dance style into tempo detection. EURASIP J. Audio Speech Music Process. 2008, 1\u201312 (2008)","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"4_CR33","unstructured":"Sigtia, S., Boulanger-Lewandowski, N., Dixon, S.: Audio chord recognition with a hybrid recurrent neural network. In: ISMIR, pp. 127\u2013133 (2015)"},{"key":"4_CR34","unstructured":"Ullrich, K., Schl\u00fcter, J., Grill, T.: Boundary detection in music structure analysis using convolutional neural networks. In: ISMIR, pp. 417\u2013422 (2014)"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Wang, J.C., Smith, J.B., Chen, J., Song, X., Wang, Y.: Supervised chorus detection for popular music using convolutional neural network and multi-task learning. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 566\u2013570. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413773"},{"key":"4_CR36","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.neucom.2019.09.054","volume":"372","author":"Y Yu","year":"2020","unstructured":"Yu, Y., Luo, S., Liu, S., Qiao, H., Liu, Y., Feng, L.: Deep attention based music genre classification. Neurocomputing 372, 84\u201391 (2020)","journal-title":"Neurocomputing"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-1645-0_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T07:24:21Z","timestamp":1729236261000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-1645-0_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819916443","9789819916450"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-1645-0_4","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"14 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Delhi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2022.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"810","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":"359","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":"44% - 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":"2.65","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":"3","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ICONIP 2022 consists of a two-volume set, LNCS & CCIS, which includes 146 and 213 papers","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)"}}]}}