{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T13:34:28Z","timestamp":1783085668899,"version":"3.54.6"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,1,8]],"date-time":"2022-01-08T00:00:00Z","timestamp":1641600000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,8]],"date-time":"2022-01-08T00:00:00Z","timestamp":1641600000000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1007\/s11042-021-11584-7","type":"journal-article","created":{"date-parts":[[2022,1,8]],"date-time":"2022-01-08T19:02:38Z","timestamp":1641668558000},"page":"5017-5031","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["End-to-end music emotion variation detection using iteratively reconstructed deep features"],"prefix":"10.1007","volume":"81","author":[{"given":"Richard","family":"Orjesek","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0478-5808","authenticated-orcid":false,"given":"Roman","family":"Jarina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michal","family":"Chmulik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,1,8]]},"reference":[{"issue":"3","key":"11584_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0173392","volume":"12","author":"A Aljanaki","year":"2017","unstructured":"Aljanaki A, Yang Y-H, Soleymani M (2017) (2017) Developing a benchmark for emotional analysis of music. PLoS ONE 12(3):1\u201322","journal-title":"PLoS ONE"},{"key":"11584_CR2","unstructured":"Amiriparian S, Gerczuk M, Coutinho E, Baird A, Ottl S, Milling M, Schuller B (2019) Emotion and themes recognition in music utilising convolutional and recurrent neural networks. In: Proc. MediaEval 2019 workshop, Sophia Antipolis, France,"},{"key":"11584_CR3","doi-asserted-by":"crossref","unstructured":"Bai J, Peng J, Shi J, Tang D, Wu Y, Li J, Luo K (2016) Dimensional music emotion recognition by valence-arousal regression. In: IEEE 15th international conference on cognitive informatics and cognitive computing. pp 42\u201349","DOI":"10.1109\/ICCI-CC.2016.7862063"},{"key":"11584_CR4","first-page":"228","volume-title":"International symposium on computer music modeling and retrieval","author":"M Barthet","year":"2012","unstructured":"Barthet M, Fazekas G, Sandler M (2012) Music emotion recognition: From content-to context-based models. International symposium on computer music modeling and retrieval. Springer, Berlin, pp 228\u2013252"},{"issue":"4","key":"11584_CR5","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1109\/JPROC.2008.916370","volume":"96","author":"MA Casey","year":"2008","unstructured":"Casey MA, Veltkamp R, Goto M, Leman M, Rhodes C, Slaney M (2008) Content-based music information retrieval: Current directions and future challenges. Proc. of the IEEE 96(4):668\u2013696","journal-title":"Proc. of the IEEE"},{"key":"11584_CR6","doi-asserted-by":"crossref","unstructured":"Cheuk KW, Luo YJ, Balamurali BT, Roig G, Herremans D (2020) Regression-based music emotion prediction using triplet neural networks. In: Proc. international joint conference on neural networks (IJCNN), July 2020. pp 1\u20137","DOI":"10.1109\/IJCNN48605.2020.9207212"},{"key":"11584_CR7","doi-asserted-by":"crossref","unstructured":"Choi K, Fazekas G, Sandler M, Cho K (2017) Convolutional recurrent neural networks for music classification. In: Proc. IEEE int. conf. acoust., speech, signal process. (ICASSP).pp 2392\u20132396","DOI":"10.1109\/ICASSP.2017.7952585"},{"issue":"4","key":"11584_CR8","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1037\/a0024700","volume":"11","author":"E Coutinho","year":"2011","unstructured":"Coutinho E, Cangelosi A (2011) Musical emotions: Predicting second-by-second subjective feelings of emotion from low-level psychoacoustic features and physiological measurements. Emotion 11(4):921","journal-title":"Emotion"},{"key":"11584_CR9","unstructured":"Coutinho E, Trigeorgis G, Zafeiriou S, Schuller B (2015) Automatically estimating emotion in music with deep long-short term memory recurrent neural networks. In: Working Notes Proc. of the MediaEval 2015 workshop, Wurzen, Germany"},{"key":"11584_CR10","unstructured":"DEAM dataset - The MediaEval database for emotional analysis of music. http:\/\/cvml.unige.ch\/databases\/DEAM. Accessed 30 Sept 2020"},{"issue":"2","key":"11584_CR11","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1109\/TAFFC.2015.2404352","volume":"6","author":"JJ Deng","year":"2015","unstructured":"Deng JJ, Leung CH (2015) Dynamic time warping for music retrieval using time series modeling of musical emotions. IEEE Transactions on Affective Computing 6(2):137\u2013151","journal-title":"IEEE Transactions on Affective Computing"},{"key":"11584_CR12","doi-asserted-by":"crossref","unstructured":"Dieleman S, Schrauwen B (2014) End-to-end learning for music audio. In: IEEE international conference on acoustics, speech and signal processing (ICASSP2014), May. pp 6964\u20136968","DOI":"10.1109\/ICASSP.2014.6854950"},{"issue":"12","key":"11584_CR13","doi-asserted-by":"publisher","first-page":"3150","DOI":"10.1109\/TMM.2019.2918739","volume":"21","author":"Y Dong","year":"2019","unstructured":"Dong Y, Yang X, Zhao X, Li J (2019) (2019) Bidirectional Convolutional Recurrent Sparse Network (BCRSN): An Efficient Model for Music Emotion Recognition. IEEE Trans. Multimedia 21(12):3150\u20133163","journal-title":"IEEE Trans. Multimedia"},{"issue":"1","key":"11584_CR14","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1177\/0305735610362821","volume":"39","author":"T Eerola","year":"2011","unstructured":"Eerola T, Vuoskoski JK (2011) A comparison of the discrete and dimensional models of emotion in music. Psychology of Music 39(1):18\u20134","journal-title":"Psychology of Music"},{"key":"11584_CR15","unstructured":"Goodfellow IJ, Warde-Farley D, Mirza M, Courville A, Bengio Y (2013) Maxout networks. In: Proc. int. conf. on machine learning (ICML\u201913), Atlanta, GA, USA, June 2013, vol 28. pp III-1319\u2013III-1327"},{"issue":"2","key":"11584_CR16","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s00799-012-0084-1","volume":"12","author":"C Inskip","year":"2012","unstructured":"Inskip C, Macfarlane A, Rafferty P (2012) Towards the disintermediation of creative music search: analysing queries to determine important facet. Int. Journal on Digital Libraries 12(2):137\u2013147","journal-title":"Int. Journal on Digital Libraries"},{"issue":"4","key":"11584_CR17","doi-asserted-by":"publisher","first-page":"1067","DOI":"10.1007\/s00521-019-04076-1","volume":"32","author":"J Kim","year":"2020","unstructured":"Kim J, Urbano J, Liem CC, Hanjalic A (2020) One deep music representation to rule them all? A comparative analysis of different representation learning strategies. Neural Computing and Applications 32(4):1067\u20131093","journal-title":"Neural Computing and Applications"},{"key":"11584_CR18","doi-asserted-by":"crossref","unstructured":"Li X, Tian J, Xu M, Ning Y, Cai L (2016) DBLSTM-based multi-scale fusion for dynamic emotion prediction in music. In: Proc. IEEE int. conf. on multimedia and expo (ICME), Jul 2016. pp 1\u20136","DOI":"10.1109\/ICME.2016.7552956"},{"key":"11584_CR19","doi-asserted-by":"crossref","unstructured":"Lim W, Jang D, Lee T (2016) Speech emotion recognition using convolutional and recurrent neural networks. In: Proc. Asia\u2013Pac. signal inf. process. assoc. annu. summit conf.. pp 1\u20134","DOI":"10.1109\/APSIPA.2016.7820699"},{"key":"11584_CR20","doi-asserted-by":"crossref","unstructured":"Malik M, Adavanne S, Drossos K, Virtanen T, Ticha D, Jarina R (2017) Stacked convolutional and recurrent neural networks for music emotion recognition. In: Proc. of sound and music computing conf., Espoo, Finland","DOI":"10.23919\/EUSIPCO.2017.8081505"},{"key":"11584_CR21","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1109\/ACCESS.2014.2333095","volume":"2","author":"K Markov","year":"2014","unstructured":"Markov K, Matsui T (2014) Music genre and emotion recognition using Gaussian processes. IEEE access 2:688\u2013697","journal-title":"IEEE access"},{"key":"11584_CR22","unstructured":"MediaEval benchmarking initiative for multimedia evaluation. http:\/\/www.multimediaeval.org\/"},{"key":"11584_CR23","unstructured":"Music Information Retrieval Evaluation eXchange. https:\/\/www.music-ir.org\/mirex"},{"key":"11584_CR24","unstructured":"OpenSmile audio feature extraction. https:\/\/www.audeering.com\/opensmile\/"},{"key":"11584_CR25","doi-asserted-by":"crossref","unstructured":"Orjesek R, Jarina R, Chmulik M, Kuba M (2019) DNN based music emotion recognition from raw audio signal. In: Proc. 29th Int. Conf. Radioelektronika, Apr 2019. IEEE, Pardubice, pp 1\u20134","DOI":"10.1109\/RADIOELEK.2019.8733572"},{"issue":"4","key":"11584_CR26","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1109\/TAFFC.2018.2820691","volume":"11","author":"R Panda","year":"2018","unstructured":"Panda R, Malheiro R, Paiva RP (2018) Novel audio features for music emotion recognition. IEEE Trans. on Affective Computing 11(4):614\u2013626","journal-title":"IEEE Trans. on Affective Computing"},{"key":"11584_CR27","unstructured":"Pons J, Nieto O, Prockup M, Schmidt E, Ehmann A, Serra X (2018) End-to-end learning for music audio tagging at scale. In: 19th int. society for music information retrieval conference, Paris, France. arXiv:1711.02520. Accessed 15 Oct 2020"},{"issue":"9","key":"11584_CR28","doi-asserted-by":"publisher","first-page":"1939","DOI":"10.1109\/JPROC.2013.2251591","volume":"101","author":"G Richard","year":"2013","unstructured":"Richard G, Sundaram S, Narayanan S (2013) An overview on perceptually motivated audio indexing and classification. Proceedings of the IEEE 101(9):1939\u20131954","journal-title":"Proceedings of the IEEE"},{"issue":"1","key":"11584_CR29","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1007\/s11042-019-08192-x","volume":"79","author":"R Sarkar","year":"2020","unstructured":"Sarkar R, Choudhury S, Dutta S, Roy A, Saha SK (2020) Recognition of emotion in music based on deep convolutional neural network. Multimedia Tools and Applications 79(1):765\u2013783","journal-title":"Multimedia Tools and Applications"},{"key":"11584_CR30","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.neucom.2016.03.020","volume":"200","author":"Roneel V Sharan","year":"2016","unstructured":"Sharan Roneel V, Moir Tom J (2016) An overview of applications and advancements in automatic sound recognition. Neurocomputing 200:22\u201334","journal-title":"Neurocomputing"},{"key":"11584_CR31","unstructured":"Thickstun J, Harchaoui Z, Kakade S (2016) Learning features of music from scratch. In: Int. conf. on learning representations ICLR. arXiv:1611.09827. Accessed 15 Oct 2020"},{"key":"11584_CR32","doi-asserted-by":"crossref","unstructured":"Tokozume Y, Harada T (2017) Learning environmental sounds with end-to-end convolutional neural network. In: Proc. of IEEE int. conf. on acoustics, speech and signal processing (ICASSP 2017). pp 2721\u20132725","DOI":"10.1109\/ICASSP.2017.7952651"},{"key":"11584_CR33","doi-asserted-by":"crossref","unstructured":"Trigeorgis G, Ringeval F, Brueckner R, Marchi E, Nicolaou MA, Schuller B, Zafeiriou S (2016) Adieu features? end-to-end speech emotion recognition using a deep convolutional recurrent network. In: Proc. IEEE Int. conf. on acoustics, speech and signal processing (ICASSP). pp 5200\u20135204","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"11584_CR34","doi-asserted-by":"crossref","unstructured":"Tzirakis P, Zhang J, Schuller BW (2018) End-to-end speech emotion recognition using deep neural networks. In: Proc. IEEE int. conf. on acoustics, speech and signal processing (ICASSP), April 2018. pp 5089\u20135093","DOI":"10.1109\/ICASSP.2018.8462677"},{"issue":"6","key":"11584_CR35","doi-asserted-by":"publisher","first-page":"1863","DOI":"10.1007\/s11042-013-1722-3","volume":"74","author":"S Wang","year":"2015","unstructured":"Wang S, Wang Z, Ji Q (2015) Multiple emotional tagging of multimedia data by exploiting dependencies among emotions. Multimedia Tools and Applications 74(6):1863\u20131883","journal-title":"Multimedia Tools and Applications"},{"key":"11584_CR36","doi-asserted-by":"crossref","unstructured":"Wei W, Zhu H, Benetos E, Wang Y (2020) A-CRNN: a domain adaptation model for sound event detection. In: Proc. IEEE int. conf. acoust., speech, signal process. (ICASSP), May 2020. pp 276\u2013280","DOI":"10.1109\/ICASSP40776.2020.9054248"},{"key":"11584_CR37","unstructured":"Weninger F, Ringeval F, Marchi E, Schuller B (2016) Discriminatively trained recurrent neural networks for continuous dimensional emotion recognition from audio. In: Proc. int. joint conf. on artificial intelligence (IJCAI\u201916), Jul 2016. pp 2196\u20132202"},{"key":"11584_CR38","unstructured":"Xu M, Li X, Xianyu H, Tian J, Meng F, Chen W (2015) Multi-scale approaches to the MediaEval 2015 emotion in music task. In: Working notes proc. of the MediaEval 2015 Workshop, Wurzen, Germany"},{"issue":"4","key":"11584_CR39","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 (2018) Review of data features-based music emotion recognition methods. Multimedia systems 24(4):365\u2013389","journal-title":"Multimedia systems"},{"key":"11584_CR40","doi-asserted-by":"crossref","unstructured":"Yang Y-H, Lin Y-C, Su Y-F, Chen HH (2008) A regression approach to music emotion recognition. IEEE Trans. Audio, Speech, and Lang. Proc. 16(2): 448\u2013457","DOI":"10.1109\/TASL.2007.911513"},{"issue":"3","key":"11584_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2168752.2168754","volume":"3","author":"YH Yang","year":"2012","unstructured":"Yang YH, Chen HH (2012) Machine recognition of music emotion: A review. ACM Transactions on Intelligent Systems and Technology 3(3):1\u201330","journal-title":"ACM Transactions on Intelligent Systems and Technology"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11584-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11584-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11584-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T06:30:03Z","timestamp":1645511403000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11584-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,8]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["11584"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11584-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,8]]},"assertion":[{"value":"30 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 September 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}