{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T01:14:17Z","timestamp":1790385257609,"version":"4.1.0"},"reference-count":107,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2019,3,12]],"date-time":"2019-03-12T00:00:00Z","timestamp":1552348800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"National Natural Science Fund for Distinguished Young Scholar","award":["61625204"],"award-info":[{"award-number":["61625204"]}]},{"name":"State Key Program of National Science Foundation of China","award":["61836006"],"award-info":[{"award-number":["61836006"]}]},{"name":"State Key Program of National Science Foundation of China","award":["61432014"],"award-info":[{"award-number":["61432014"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1007\/s00530-019-00607-x","type":"journal-article","created":{"date-parts":[[2019,3,12]],"date-time":"2019-03-12T05:44:57Z","timestamp":1552369497000},"page":"617-638","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Deep learning-based automatic downbeat tracking: a brief review"],"prefix":"10.1007","volume":"25","author":[{"given":"Bijue","family":"Jia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6551-3884","authenticated-orcid":false,"given":"Jiancheng","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dayiheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,3,12]]},"reference":[{"key":"607_CR1","volume-title":"A Generative Theory of Tonal Music","author":"F Lerdahl","year":"1985","unstructured":"Lerdahl, F., Jackendoff, R.S.: A Generative Theory of Tonal Music. MIT Press, Cambridge (1985)"},{"key":"607_CR2","unstructured":"Sigtia, S., Benetos, E., Cherla, S., Weyde, T., Garcez, A.S.d., Dixon, S.: RNN-based music language models for improving automatic music transcription. In:\u00a0International Society for Music Information Retrieval Conference (2014)"},{"issue":"5","key":"607_CR3","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1109\/TASLP.2016.2533858","volume":"24","author":"S Sigtia","year":"2016","unstructured":"Sigtia, S., Benetos, E., Dixon, S.: An end-to-end neural network for polyphonic piano music transcription. IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP) 24(5), 927\u2013939 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP)"},{"key":"607_CR4","unstructured":"Sturm, B.L., Santos, J.a.F., Ben-Tal, O., Korshunova, I.: Music transcription modelling and composition using deep learning (2016). \narXiv:1604.08723"},{"issue":"12","key":"607_CR5","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."},{"issue":"8","key":"607_CR6","doi-asserted-by":"publisher","first-page":"2249","DOI":"10.1109\/TASL.2010.2098870","volume":"19","author":"L Oudre","year":"2011","unstructured":"Oudre, L., F\u00e9votte, C., Grenier, Y.: Probabilistic template-based chord recognition. IEEE Trans. Audio Speech Lang. Process. 19(8), 2249\u20132259 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"607_CR7","unstructured":"Di Giorgi, B., Zanoni, M., Sarti, A., Tubaro, S.: Automatic chord recognition based on the probabilistic modeling of diatonic modal harmony. Multidimensional Systems (nDS). In: Proceedings of the 8th International Workshop on (VDE, 2013), pp. 1\u20136 (2013)"},{"issue":"1","key":"607_CR8","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/MMUL.2006.3","volume":"13","author":"NC Maddage","year":"2006","unstructured":"Maddage, N.C.: Automatic structure detection for popular music. IEEE Multimed. 13(1), 65\u201377 (2006)","journal-title":"IEEE Multimed."},{"issue":"5","key":"607_CR9","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1109\/TMM.2014.2310701","volume":"16","author":"J Serra","year":"2014","unstructured":"Serra, J., M\u00fcller, M., Grosche, P., Arcos, J.L.: Unsupervised music structure annotation by time series structure features and segment similarity. IEEE Trans. Multimed. 16(5), 1229\u20131240 (2014)","journal-title":"IEEE Trans. Multimed."},{"key":"607_CR10","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.patrec.2013.10.021","volume":"38","author":"Y Panagakis","year":"2014","unstructured":"Panagakis, Y., Kotropoulos, C.: Elastic net subspace clustering applied to pop\/rock music structure analysis. Pattern Recogn. Lett. 38, 46\u201353 (2014)","journal-title":"Pattern Recogn. Lett."},{"key":"607_CR11","unstructured":"Pauwels, J., Kaiser, F., Peeters, G.: Combining Harmony-Based and Novelty-Based Approaches for Structural Segmentation. In:\u00a0International Society for Music Information Retrieval Conference, pp. 601\u2013606 (2013)"},{"key":"607_CR12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21945-5","volume-title":"Fundamentals of Music Processing: Audio, Analysis, Algorithms, Applications","author":"M M\u00fcller","year":"2015","unstructured":"M\u00fcller, M.: Fundamentals of Music Processing: Audio, Analysis, Algorithms, Applications. Springer, New York (2015)"},{"key":"607_CR13","unstructured":"Downie, J.S.: Music Information Retrieval Evaluation eXchange. \nhttp:\/\/www.music-ir.org\/mirex\/wiki\/MIREX_HOME"},{"issue":"1","key":"607_CR14","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1002\/aris.1440370108","volume":"37","author":"JS Downie","year":"2003","unstructured":"Downie, J.S.: Music information retrieval. Ann. Rev. Inf. Sci. Technol. 37(1), 295\u2013340 (2003)","journal-title":"Ann. Rev. Inf. Sci. Technol."},{"key":"607_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13287-2","volume-title":"Music Recommendation","author":"O Celma","year":"2010","unstructured":"Celma, O.: Music Recommendation. Springer, Berlin, Heidelberg (2010)"},{"key":"607_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-45402-2_151","volume-title":"A Music Recommendation Method with Emotion Recognition Using Ranked Attributes","author":"SH Park","year":"2015","unstructured":"Park, S.H., Ihm, S.Y., Jang, W.I., Nasridinov, A., Park, Y.H.: A Music Recommendation Method with Emotion Recognition Using Ranked Attributes. Springer, Berlin, Heidelberg (2015)"},{"issue":"4","key":"607_CR17","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/s00530-017-0559-4","volume":"24","author":"X Yang","year":"2018","unstructured":"Yang, X., Dong, Y., Li, J.: Review of data features-based music emotion recognition methods. Multimed. Syst. 24(4), 365\u2013389 (2018)","journal-title":"Multimed. Syst."},{"key":"607_CR18","unstructured":"Typke, R., Wiering, F., Veltkamp, R.C.: A survey of music information retrieval systems. In: Proc. 6th International Conference on Music Information Retrieval, pp. 153\u2013160. Queen Mary, University of London, London (2005)"},{"issue":"4","key":"607_CR19","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1109\/JPROC.2008.916370","volume":"96","author":"MA Casey","year":"2008","unstructured":"Casey, M.A., Veltkamp, R., Goto, M., Leman, M., Rhodes, C., Slaney, M.: Content-based music information retrieval: Current directions and future challenges. Proc. IEEE 96(4), 668\u2013696 (2008)","journal-title":"Proc. IEEE"},{"issue":"4","key":"607_CR20","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1250\/ast.29.247","volume":"29","author":"JS Downie","year":"2008","unstructured":"Downie, J.S.: The music information retrieval evaluation exchange (2005\u20132007): A window into music information retrieval research. Acoust. Sci. Technol. 29(4), 247\u2013255 (2008)","journal-title":"Acoust. Sci. Technol."},{"key":"607_CR21","doi-asserted-by":"crossref","unstructured":"Goto, M., Muraoka, Y.: A beat tracking system for acoustic signals of music. In: Proceedings of the Second ACM International Conference on Multimedia, pp. 365\u2013372. ACM, New York (1994)","DOI":"10.1145\/192593.192700"},{"key":"607_CR22","doi-asserted-by":"crossref","unstructured":"Goto, M., Muraoka, Y.: A Real-Time Beat Tracking System for Audio Signals.\u00a0In: ICMC (1995)","DOI":"10.1145\/192593.192700"},{"issue":"2","key":"607_CR23","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1076\/jnmr.30.2.159.7114","volume":"30","author":"M Goto","year":"2001","unstructured":"Goto, M.: An audio-based real-time beat tracking system for music with or without drum-sounds. J. New Music Res. 30(2), 159\u2013171 (2001)","journal-title":"J. New Music Res."},{"key":"607_CR24","doi-asserted-by":"crossref","unstructured":"Davies, M.E., Plumbley, M.D.: Beat tracking with a two state model [music applications]. In: IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (ICASSP'05), vol. 3, pp. iii\u2013241. IEEE (2005)","DOI":"10.1109\/ICASSP.2005.1415691"},{"key":"607_CR25","unstructured":"Sepp\u00e4nen, J., Eronen, A.J., Hiipakka, J.: Joint Beat\u00a0& Tatum Tracking from Music Signals.\u00a0In: ISMIR, pp. 23\u201328 (2006)"},{"key":"607_CR26","doi-asserted-by":"crossref","unstructured":"Gkiokas, A., Katsouros, V., Carayannis, G., Stajylakis, T.: Music tempo estimation and beat tracking by applying source separation and metrical relations. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 421\u2013424. IEEE (2012)","DOI":"10.1109\/ICASSP.2012.6287906"},{"issue":"6","key":"607_CR27","doi-asserted-by":"publisher","first-page":"1754","DOI":"10.1109\/TASL.2010.2098869","volume":"19","author":"G Peeters","year":"2011","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 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"607_CR28","unstructured":"Krebs, F., B\u00f6ck, S., Widmer, G.: Rhythmic Pattern Modeling for Beat and Downbeat Tracking in Musical Audio. In: ISMIR, pp. 227\u2013232 (2013)"},{"key":"607_CR29","unstructured":"Krebs, F., Korzeniowski, F., Grachten, M., Widmer, G.: Unsupervised learning and refinement of rhythmic patterns for beat and downbeat tracking. In: 2014 Proceedings of the 22nd European, Signal Processing Conference (EUSIPCO), pp. 611\u2013615. IEEE (2014)"},{"key":"607_CR30","unstructured":"B\u00f6ck, S., Krebs, F., Widmer, G.: Joint Beat and Downbeat Tracking with Recurrent Neural Networks. In:\u00a0ISMIR, pp. 255\u2013261 (2016)"},{"issue":"3\u20134","key":"607_CR31","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/S0167-6393(98)00076-4","volume":"27","author":"M Goto","year":"1999","unstructured":"Goto, M., Muraoka, Y.: Real-time beat tracking for drumless audio signals: Chord change detection for musical decisions. Speech Commun. 27(3\u20134), 311 (1999)","journal-title":"Speech Commun."},{"key":"607_CR32","unstructured":"Davies, M.E., Plumbley, M.D.: A spectral difference approach to downbeat extraction in musical audio. In:\u00a0Proceedings of the 14th European Signal Processing Conference (EUSIPCO), pp. 1\u20134\u00a0(2006)"},{"key":"607_CR33","doi-asserted-by":"crossref","unstructured":"Durand, S., David, B., Richard, G.: Enhancing downbeat detection when facing different music styles. In:\u00a0IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 3132\u20133136 (2014)","DOI":"10.1109\/ICASSP.2014.6854177"},{"issue":"1","key":"607_CR34","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1109\/TSA.2005.854090","volume":"14","author":"AP Klapuri","year":"2006","unstructured":"Klapuri, A.P., Eronen, A.J., Astola, J.T.: Analysis of the meter of acoustic musical signals. IEEE Trans. Audio Speech Lang. Process. 14(1), 342\u2013355 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"607_CR35","unstructured":"Jehan, T.: Downbeat prediction by listening and learning.\u00a0In: IEEE Workshop on Applications of Signal Processing to Audio and Acoustics. pp. 267\u2013270. IEEE (2005)"},{"issue":"1","key":"607_CR36","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1109\/TASL.2010.2045236","volume":"19","author":"H Papadopoulos","year":"2011","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 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"607_CR37","unstructured":"G\u00e4rtner, D.: Unsupervised learning of the downbeat in drum patterns. In: Audio Engineering Society Conference: 53rd International Conference: Semantic Audio. Audio Engineering Society (2014)"},{"key":"607_CR38","unstructured":"Hockman, J., Davies, M.E., Fujinaga, I.: One in the Jungle: Downbeat Detection in Hardcore, Jungle, and Drum and Bass. In:\u00a0ISMIR, pp. 169\u2013174 (2012)"},{"issue":"1","key":"607_CR39","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1080\/09298215.2013.879902","volume":"43","author":"A Srinivasamurthy","year":"2014","unstructured":"Srinivasamurthy, A., Holzapfel, A., Serra, X.: In search of automatic rhythm analysis methods for turkish and indian art music. J. New Music Res. 43(1), 94\u2013114 (2014)","journal-title":"J. New Music Res."},{"key":"607_CR40","first-page":"28","volume":"27","author":"H Allan","year":"2004","unstructured":"Allan, H.: Bar lines and beyond-meter tracking in digital audio. M\u00e9moire de DEA School Inf. Univ. Edinb. 27, 28 (2004)","journal-title":"M\u00e9moire de DEA School Inf. Univ. Edinb."},{"key":"607_CR41","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep Learning, vol. 1. MIT Press, Cambridge (2016)"},{"key":"607_CR42","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, Y.: Improving content-based and hybrid music recommendation using deep learning.\u00a0In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 627\u2013636. ACM, New York (2014)","DOI":"10.1145\/2647868.2654940"},{"key":"607_CR43","doi-asserted-by":"crossref","unstructured":"Yan, Y., Chen, M., Shyu, M.L., Chen, S.C.: Deep learning for imbalanced multimedia data classification. In: 2015 IEEE International Symposium on Multimedia (ISM), pp. 483\u2013488. IEEE (2015)","DOI":"10.1109\/ISM.2015.126"},{"key":"607_CR44","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1007\/978-3-319-42294-7_28","volume-title":"Intelligent Computing Theories and Application","author":"Hui Zou","year":"2016","unstructured":"Zou, H., Du, J.X., Zhai, C.M., Wang, J.: Deep learning and shared representation space learning based cross-modal multimedia retrieval. In: International Conference on Intelligent Computing, pp. 322\u2013331. Springer, New York (2016)"},{"issue":"3","key":"607_CR45","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1007\/s00530-015-0485-2","volume":"23","author":"W Nie","year":"2017","unstructured":"Nie, W., Cao, Q., Liu, A., Su, Y.: Convolutional deep learning for 3d object retrieval. Multimed. Syst. 23(3), 325\u2013332 (2017)","journal-title":"Multimed. Syst."},{"key":"607_CR46","doi-asserted-by":"crossref","unstructured":"Durand, S., Bello, J.P., David, B., Richard, G.: Downbeat tracking with multiple features and deep neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 409\u2013413. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178001"},{"key":"607_CR47","doi-asserted-by":"crossref","unstructured":"Durand, S., Bello, J.P., David, B., Richard, G.: Feature adapted convolutional neural networks for downbeat tracking. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 296\u2013300. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7471684"},{"issue":"1","key":"607_CR48","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1109\/TASLP.2016.2623565","volume":"25","author":"S Durand","year":"2017","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. (TASLP) 25(1), 76\u201389 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP)"},{"key":"607_CR49","unstructured":"Krebs, F., B\u00f6ck, S., Dorfer, M., Widmer, G.: Downbeat Tracking Using Beat Synchronous Features with Recurrent Neural Networks. In: ISMIR, pp. 129\u2013135 (2016)"},{"key":"607_CR50","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/978-3-642-24797-2_2","volume-title":"Supervised sequence labelling with recurrent neural networks","author":"A Graves","year":"2012","unstructured":"Graves, A.: Supervised sequence labelling. Supervised sequence labelling with recurrent neural networks. Springer, Berlin, Heidelberg,\u00a0pp. 5\u201313\u00a0(2012)"},{"issue":"3","key":"607_CR51","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1109\/34.667881","volume":"20","author":"J Kittler","year":"1998","unstructured":"Kittler, J., Hatef, M., Duin, R.P., Matas, J.: On combining classifiers. IEEE Trans. Pattern Anal. Mach. Intell. 20(3), 226\u2013239 (1998)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"607_CR52","unstructured":"Grosche, P., M\u00fcller, M.: Tempogram toolbox: Matlab implementations for tempo and pulse analysis of music recordings. In: Proceedings of the 12th International Conference on Music Information Retrieval (ISMIR). Miami, FL, USA (2011)"},{"issue":"1","key":"607_CR53","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1080\/09298210701653310","volume":"36","author":"S Dixon","year":"2007","unstructured":"Dixon, S.: Evaluation of the audio beat tracking system beatroot. J. New Music Res. 36(1), 39\u201350 (2007)","journal-title":"J. New Music Res."},{"key":"607_CR54","doi-asserted-by":"crossref","unstructured":"Khadkevich, M., Fillon, T., Richard, G., Omologo, M.: A probabilistic approach to simultaneous extraction of beats and downbeats. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 445\u2013448. IEEE (2012)","DOI":"10.1109\/ICASSP.2012.6287912"},{"key":"607_CR55","unstructured":"Holzapfel, A., Krebs, F., Srinivasamurthy, A.: Tracking the \u201codd\u201d: Meter inference in a culturally diverse music corpus. In: ISMIR-International Conference on Music Information Retrieval, pp. 425\u2013430. ISMIR (2014)"},{"key":"607_CR56","volume-title":"Music Cultures of the Pacific, the Near East, and Asia","author":"WP Malm","year":"1996","unstructured":"Malm, W.P.: Music Cultures of the Pacific, the Near East, and Asia. Pearson College Division, London (1996)"},{"key":"607_CR57","unstructured":"Bello, J.P., Pickens, J.: A Robust Mid-Level Representation for Harmonic Content in Music Signals. In: ISMIR, vol. 5, pp. 304\u2013311 (2005)"},{"key":"607_CR58","unstructured":"M\u00fcller, M., Ewert, S.: Chroma Toolbox: MATLAB implementations for extracting variants of chroma-based audio features. In: Proceedings of the 12th International Conference on Music Information Retrieval (ISMIR) (2011)"},{"key":"607_CR59","unstructured":"Brookes, M.: Voicebox: Speech processing toolbox for matlab, vol. 47. Software. Available from\u00a0\nhttp:\/\/www.ee.ic.ac.uk\/hp\/staff\/dmb\/voicebox\/voicebox.html\n\n (2011)"},{"issue":"4","key":"607_CR60","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1525\/mp.2003.20.4.431","volume":"20","author":"PQ Pfordresher","year":"2003","unstructured":"Pfordresher, P.Q.: The role of melodic and rhythmic accents in musical structure. Music Percept. Interdiscip. J. 20(4), 431\u2013464 (2003)","journal-title":"Music Percept. Interdiscip. J."},{"issue":"5","key":"607_CR61","doi-asserted-by":"publisher","first-page":"956","DOI":"10.1037\/0096-1523.30.5.956","volume":"30","author":"EE Hannon","year":"2004","unstructured":"Hannon, E.E., Snyder, J.S., Eerola, T., Krumhansl, C.L.: The role of melodic and temporal cues in perceiving musical meter. J. Exp. Psychol. Human Percept. Perform. 30(5), 956 (2004)","journal-title":"J. Exp. Psychol. Human Percept. Perform."},{"issue":"1","key":"607_CR62","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1037\/a0013482","volume":"35","author":"RJ Ellis","year":"2009","unstructured":"Ellis, R.J., Jones, M.R.: The role of accent salience and joint accent structure in meter perception. J. Exp. Psychol. Human Percept. Perform. 35(1), 264 (2009)","journal-title":"J. Exp. Psychol. Human Percept. Perform."},{"key":"607_CR63","unstructured":"Florian, K., Andre, H., Ajay, S.: Mirex 2014 audio downbeat tracking evaluation: Khs1. \nhttp:\/\/www.music-ir.org\/mirex\/abstracts\/2014\/KSH1.pdf\n\n (2014)"},{"key":"607_CR64","unstructured":"Florian, K., Gerhard, W.: Mirex 2014 audio downbeat tracking evaluation: Fk1. \nhttp:\/\/www.music-ir.org\/mirex\/abstracts\/2014\/FK3.pdf\n\n (2014)"},{"key":"607_CR65","unstructured":"Florian, K., Gerhard, W.: Mirex 2014 audio downbeat tracking evaluation: Fk2. \nhttp:\/\/www.music-ir.org\/mirex\/abstracts\/2014\/FK4.pdf\n\n (2014)"},{"key":"607_CR66","unstructured":"Florian, K., Sebastian, B.: Mirex 2015 audio beat and downbeat tracking submissions: Fk1, fk2, fk3, fk4, fk5, fk6. \nhttp:\/\/www.music-ir.org\/mirex\/abstracts\/2015\/FK2.pdf\n\n (2015)"},{"key":"607_CR67","unstructured":"Chris, C., Emmanouil, B., Matthias, M., Matthew, D.E.P., Simon, D., Christian, L., Katy, N., Dan, S.: Mirex 2016: Vamp plugins from the centre for digital music. \nhttp:\/\/www.music-ir.org\/mirex\/abstracts\/2016\/CD4.pdf\n\n (2016)"},{"key":"607_CR68","unstructured":"Matthew, D., Adam, S., Andrew, R.: Downbeater: Audio downbeat estimation task. \nhttp:\/\/www.music-ir.org\/mirex\/abstracts\/2016\/DSR1.pdf\n\n (2016)"},{"key":"607_CR69","unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In:\u00a0Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 315\u2013323 (2011)"},{"key":"607_CR70","unstructured":"Goodfellow, I.J., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks (2013). \narXiv:1302.4389"},{"key":"607_CR71","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Chellappa, R.: Computation of optical flow using a neural network. In: IEEE International Conference on Neural Networks, vol. 27, pp. 71\u201378 (1988)","DOI":"10.1109\/ICNN.1988.23914"},{"key":"607_CR72","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Kingsbury, B., Mohamed, A.r., Dahl, G.E., Saon, G., Soltau, H., Beran, T., Aravkin, A.Y., Ramabhadran, B.: Improvements to deep convolutional neural networks for LVCSR. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 315\u2013320. IEEE (2013)","DOI":"10.1109\/ASRU.2013.6707749"},{"issue":"6088","key":"607_CR73","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533 (1986)","journal-title":"Nature"},{"issue":"8","key":"607_CR74","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"607_CR75","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using rnn encoder-decoder for statistical machine translation (2014). \narXiv:1406.1078"},{"issue":"5","key":"607_CR76","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."},{"key":"607_CR77","unstructured":"Harte, C.: Towards automatic extraction of harmony information from music signals. Ph.D. thesis (2010)"},{"key":"607_CR78","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, Tech. Rep. C4DM-TR-09-06 (2009)"},{"key":"607_CR79","doi-asserted-by":"crossref","unstructured":"Srinivasamurthy, A., Serra, X.: A supervised approach to hierarchical metrical cycle tracking from audio music recordings. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5217\u20135221. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854598"},{"key":"607_CR80","unstructured":"Srinivasamurthy, A., Holzapfel, A., Cemgil, A.T., Serra, X.: Particle filters for efficient meter tracking with dynamic bayesian networks. In: International Society for Music Information Retrieval Conference (ISMIR)\u00a0(2015)"},{"issue":"5","key":"607_CR81","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TSA.2002.800560","volume":"10","author":"G Tzanetakis","year":"2002","unstructured":"Tzanetakis, G., Cook, P.: Musical genre classification of audio signals. IEEE Trans. Speech Audio Process. 10(5), 293\u2013302 (2002)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"607_CR82","unstructured":"Marchand, U., Peeters, G.: Swing ratio estimation. Digital Audio Effects 2015 (Dafx15) (2015)"},{"key":"607_CR83","unstructured":"Hainsworth, S.W.: Techniques for the automated analysis of musical audio. PhD thesis. University of Cambridge (2003)"},{"issue":"15","key":"607_CR84","doi-asserted-by":"publisher","first-page":"927847","DOI":"10.1155\/S1110865704408099","volume":"2004","author":"SW Hainsworth","year":"2004","unstructured":"Hainsworth, S.W., Macleod, M.D.: Particle filtering applied to musical tempo tracking. EURASIP J. Adv. Signal Process. 2004(15), 927847 (2004)","journal-title":"EURASIP J. Adv. Signal Process."},{"issue":"7\/8","key":"607_CR85","doi-asserted-by":"publisher","first-page":"493","DOI":"10.17743\/jaes.2016.0025","volume":"64","author":"BD Giorgi","year":"2016","unstructured":"Giorgi, B.D., Zanoni, M., B\u00f6ck, S., Sarti, A.: Multipath beat tracking. J. Audio Eng. Soc. 64(7\/8), 493\u2013502 (2016)","journal-title":"J. Audio Eng. Soc."},{"issue":"1","key":"607_CR86","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1017\/S026114301000067X","volume":"30","author":"T Clercq De","year":"2011","unstructured":"De Clercq, T., Temperley, D.: A corpus analysis of rock harmony. Popul. Music 30(1), 47\u201370 (2011)","journal-title":"Popul. Music"},{"key":"607_CR87","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)"},{"key":"607_CR88","unstructured":"Goto, M., et al.: Development of the RWC music database. In: Proceedings of the 18th International Congress on Acoustics (ICA 2004), vol. 1, pp. 553\u2013556 (2004)"},{"key":"607_CR89","unstructured":"Goto, M.: AIST Annotation for the RWC Music Database. In: ISMIR, pp. 359\u2013360 (2006)"},{"key":"607_CR90","unstructured":"Livshin, A., Rodex, X.: The importance of cross database evaluation in sound classification. In:\u00a0ISMIR (2003)"},{"key":"607_CR91","unstructured":"Simon, D., Juan, B., P., Bertrand, D., Ga\u00ebl, R.: Mirex 2014 audio downbeat estimation evaluation: Db1. \nhttp:\/\/www.music-ir.org\/mirex\/abstracts\/2014\/DBDR2.pdf\n\n (2014)"},{"key":"607_CR92","unstructured":"Simon, D., Juan, B., P., Bertrand, D., Ga\u00ebl, R.: Mirex 2015 audio downbeat estimation submissions: Drdb2 and drdb3. \nhttp:\/\/www.music-ir.org\/mirex\/abstracts\/2015\/DBDR2.pdf\n\n (2015)"},{"key":"607_CR93","unstructured":"Simon, D., Juan, P.B., Bertrand, D., Ga\u00ebl, R.: Mirex 2016 audio downbeat estimation evaluation: Dbdr_nobe. \nhttp:\/\/www.music-ir.org\/mirex\/abstracts\/2016\/DBDR1.pdf\n\n (2016)"},{"key":"607_CR94","unstructured":"Florian, K., Sebastian, B.: Mirex 2016 audio downbeat tracking submissions: Kb1, kb2. \nhttp:\/\/www.music-ir.org\/mirex\/abstracts\/2016\/KBDW1.pdf\n\n (2016)"},{"key":"607_CR95","unstructured":"Sebastian, B., Florian, K.: Mirex 2016 submission bk4. \nhttp:\/\/www.music-ir.org\/mirex\/abstracts\/2016\/BK4.pdf\n\n (2016)"},{"key":"607_CR96","doi-asserted-by":"crossref","unstructured":"B\u00f6ck, S., Korzeniowski, F., Schl\u00fcter, J., Krebs, F., Widmer, G.: Madmom: A new Python audio and music signal processing library. In: Proceedings of the 2016 ACM on Multimedia Conference, pp. 1174\u20131178. ACM (2016)","DOI":"10.1145\/2964284.2973795"},{"key":"607_CR97","unstructured":"Lartillot, O., Toiviainen, P.: A Matlab toolbox for musical feature extraction from audio. In:\u00a0International conference on digital audio effects, pp. 237\u2013244. Bordeaux, FR\u00a0(2007)"},{"key":"607_CR98","doi-asserted-by":"crossref","unstructured":"Latrillot, O., Toiviainen, P.: MIR in Matlab: A toolbox for musical feature extraction. In: Proceedings of the International Conference on Music Information Retrieval (2007)","DOI":"10.1007\/978-3-540-78246-9_31"},{"key":"607_CR99","doi-asserted-by":"crossref","unstructured":"Bogdanov, D., Wack, N., G\u00f3mez, E., Gulati, S., Herrera, P., Mayor, O., Roma, G., Salamon, J., Zapata, J., Serra, X.: ESSENTIA: an open-source library for sound and music analysis. In:\u00a0Proceedings of the 21st ACM international conference on Multimedia, pp. 855\u2013858. ACM (2013)","DOI":"10.1145\/2502081.2502229"},{"key":"607_CR100","doi-asserted-by":"crossref","unstructured":"McFee, B., Raffel, C., Liang, D., Ellis, D.P., McVicar, M., Battenberg, E., Nieto, O.: librosa: Audio and music signal analysis in python. In: Proceedings of the 14th Python in Science Conference, pp. 18\u201325 (2015)","DOI":"10.25080\/Majora-7b98e3ed-003"},{"issue":"5","key":"607_CR101","first-page":"817","volume":"23","author":"F Krebs","year":"2015","unstructured":"Krebs, F., Holzapfel, A., Cemgil, A.T., Widmer, G.: Inferring metrical structure in music using particle filters. IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP) 23(5), 817\u2013827 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP)"},{"key":"607_CR102","unstructured":"Mor, N., Wolf, L., Polyak, A., Taigman, Y.: A universal music translation network (2018). \narXiv:1805.07848"},{"key":"607_CR103","doi-asserted-by":"crossref","unstructured":"Zhang, H., Yang, Y., Luan, H., Yang, S., Chua, T.S.: Start from scratch: Towards automatically identifying, modeling, and naming visual attributes. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 187\u2013196. ACM (2014)","DOI":"10.1145\/2647868.2654915"},{"key":"607_CR104","doi-asserted-by":"crossref","unstructured":"Dieleman, S., Schrauwen, B.: End-to-end learning for music audio. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6964\u20136968. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854950"},{"key":"607_CR105","doi-asserted-by":"crossref","unstructured":"Miao, Y., Gowayyed, M., Metze, F.: EESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 167\u2013174. IEEE (2015)","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"607_CR106","unstructured":"Ma, X., Hovy, E.: End-to-end sequence labeling via bi-directional lstm-cnns-crf (2016). \narXiv:1603.01354"},{"key":"607_CR107","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, M., Hong, R., Chua, T.S.: Play and rewind: Optimizing binary representations of videos by self-supervised temporal hashing. In: Proceedings of the 2016 ACM on Multimedia Conference, pp. 781\u2013790. ACM (2016)","DOI":"10.1145\/2964284.2964308"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-019-00607-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00530-019-00607-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-019-00607-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,3,10]],"date-time":"2020-03-10T20:10:45Z","timestamp":1583871045000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00530-019-00607-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,12]]},"references-count":107,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["607"],"URL":"https:\/\/doi.org\/10.1007\/s00530-019-00607-x","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3,12]]},"assertion":[{"value":"12 March 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}