{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T11:03:34Z","timestamp":1776078214590,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2020,11,26]],"date-time":"2020-11-26T00:00:00Z","timestamp":1606348800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,11,26]],"date-time":"2020-11-26T00:00:00Z","timestamp":1606348800000},"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":["Int J Speech Technol"],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1007\/s10772-020-09781-0","type":"journal-article","created":{"date-parts":[[2020,11,26]],"date-time":"2020-11-26T16:02:34Z","timestamp":1606406554000},"page":"571-580","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Development of music emotion classification system using convolution neural network"],"prefix":"10.1007","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7150-0470","authenticated-orcid":false,"given":"Deepti","family":"Chaudhary","sequence":"first","affiliation":[]},{"given":"Niraj Pratap","family":"Singh","sequence":"additional","affiliation":[]},{"given":"Sachin","family":"Singh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,26]]},"reference":[{"key":"9781_CR1","unstructured":"Aljanaki, A. (2016). Emotion in music: Representation and computational modeling."},{"issue":"2","key":"9781_CR2","doi-asserted-by":"publisher","first-page":"88","DOI":"10.5391\/IJFIS.2019.19.2.88","volume":"19","author":"B Bhattarai","year":"2019","unstructured":"Bhattarai, B., & Lee, J. (2019). Automatic music mood detection using transfer learning and multilayer perceptron. International Journal of Fuzzy Logic and Intelligent Systems, 19(2), 88\u201396.","journal-title":"International Journal of Fuzzy Logic and Intelligent Systems"},{"issue":"2","key":"9781_CR3","doi-asserted-by":"publisher","first-page":"1622","DOI":"10.2991\/ijcis.d.191216.001","volume":"12","author":"M Bilal Er","year":"2019","unstructured":"Bilal Er, M., & Aydilek, I. B. (2019). Music emotion recognition by using chroma spectrogram and deep visual features. Journal of Computational Intelligent Systems, 12(2), 1622\u20131634.","journal-title":"Journal of Computational Intelligent Systems"},{"key":"9781_CR4","unstructured":"Bischke, B., Helber, P., Schulze, C., Srinivasan, V., Dengel, A., & Borth, D. (2017). The multimedia satellite task at mediaeval 2017: Emergency response for flooding events. In CEUR workshop proceedings, September 13\u201315, 2017, Ireland, Dublin."},{"key":"9781_CR5","volume-title":"Pattern recognition and machine learning","author":"CM Bishop","year":"2006","unstructured":"Bishop, C. M. (2006). Pattern recognition and machine learning. New York: Springer."},{"key":"9781_CR6","unstructured":"Cabrera, D., Ferguson, S., & Schubert, E. (2007). Psysound3: Software for acoustical and psychoacoustical analysis of sound recordings. In Proceedings of the 13th international conference on auditory display, June 26\u201329, 2007, Montr\u00e9al, Canada."},{"key":"9781_CR7","unstructured":"Carruthers, A., & Carruthers, J. (1990). Handwritten digit recognition with a back-propagation network."},{"key":"9781_CR8","doi-asserted-by":"crossref","unstructured":"Chiang, W. C., Wang, J. S., & Hsu, Y. L. (2014). A music emotion recognition algorithm with hierarchical SVM based classifiers. In International symposium on computer, consumer and control (pp. 1249\u20131252), June 10\u201312, 2014, Taichung, Taiwan.","DOI":"10.1109\/IS3C.2014.323"},{"key":"9781_CR9","doi-asserted-by":"crossref","unstructured":"D\u00f6rfler, M., Bammer, R., & Grill, T. (2017). Inside the spectrogram: Convolutional Neural Networks in audio processing. In International conference on sampling theory and applications (SampTA) (Vol. 1, pp. 152\u2013155), July 3\u20137, 2017, Tallin, Estonia.","DOI":"10.1109\/SAMPTA.2017.8024472"},{"issue":"3\u20134","key":"9781_CR10","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1080\/02699939208411068","volume":"6","author":"P Ekman","year":"1992","unstructured":"Ekman, P. (1992). An argument for basic emotions. Cognition and Emotion, 6(3\u20134), 169\u2013200.","journal-title":"Cognition and Emotion"},{"key":"9781_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-01562-9","volume-title":"Speech Analysis, Synthesis, and Perception","author":"JL Flanagan","year":"1972","unstructured":"Flanagan, J. L., Allen, J. B., & Hasegawa-Johnson, M. A. (1972). Speech Analysis, Synthesis, and Perception (2nd ed.). Berlin: NewYork.","edition":"2"},{"key":"9781_CR12","first-page":"1","volume":"2","author":"Y Hou","year":"2019","unstructured":"Hou, Y., & Chen, S. (2019). Distinguishing different emotions evoked by music via electroencephalographic signals. Computational Intelligence and Neuroscience, 2, 1\u201318.","journal-title":"Computational Intelligence and Neuroscience"},{"issue":"2","key":"9781_CR13","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1002\/asi.23649","volume":"68","author":"X Hu","year":"2017","unstructured":"Hu, X. (2017). A framework for evaluating multimodal music mood classification. Journal of the Association for Information Science and Technology, 68(2), 273\u2013285.","journal-title":"Journal of the Association for Information Science and Technology"},{"key":"9781_CR14","unstructured":"Hu, X., Downie, J. S., Laurier, C., Bay, M., & Ehmann, A. F. (2008) The 2007 MIREX audio mood classification task\u202f: Lessons learned. In Proceedings of 9th international conference on music information retrieval (pp. 462\u2013467), September 14\u201318, 2008, Philadelphia, PA, United States."},{"key":"9781_CR15","unstructured":"Kim, Y. E., Williamson, D. S., & Pilli, S. (2006). Towards quantifying the \u2018album effect\u2019 in artist identification. In Proceedings of 7th international conference on music information retrieval (pp. 393\u2013394), October 8\u201312, 2006, Victoria, Canada."},{"issue":"1","key":"9781_CR16","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/T-AFFC.2011.15","volume":"3","author":"S Koelstra","year":"2012","unstructured":"Koelstra, S., et al. (2012). DEAP: A database for emotion analysis; Using physiological signals. IEEE Transactions on Affective Computing, 3(1), 18\u201331.","journal-title":"IEEE Transactions on Affective Computing"},{"issue":"11","key":"9781_CR17","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of IEEE, 86(11), 2278\u20132324.","journal-title":"Proceedings of IEEE"},{"issue":"8","key":"9781_CR18","doi-asserted-by":"publisher","first-page":"1208","DOI":"10.1109\/LSP.2017.2713830","volume":"24","author":"J Lee","year":"2017","unstructured":"Lee, J., & Nam, J. (2017). Multi-level and multi-scale feature aggregation using pretrained convolutional neural networks for music auto-tagging. IEEE Signal Processing Letters, 24(8), 1208\u20131212.","journal-title":"IEEE Signal Processing Letters"},{"issue":"10","key":"9781_CR19","doi-asserted-by":"publisher","first-page":"3501","DOI":"10.3390\/app10103501","volume":"10","author":"MS Lee","year":"2020","unstructured":"Lee, M. S., Lee, Y. K., Lim, M. T., & Kang, T. K. (2020). Emotion recognition using convolutional neural network with selected statistical photoplethysmogram features. Applied Sciences, 10(10), 3501.","journal-title":"Applied Sciences"},{"key":"9781_CR20","doi-asserted-by":"crossref","unstructured":"Liu, T., Han, L., Ma, L., & Guo, D. (2018). Audio-based deep music emotion recognition. In Proceedings of AIP (Vol. 1967), May 2018.","DOI":"10.1063\/1.5039095"},{"key":"9781_CR21","unstructured":"Liu, X., Chen, Q., Wu, X., Liu, Y., & Liu, Y. (2017). CNN based music emotion classification."},{"key":"9781_CR22","doi-asserted-by":"crossref","unstructured":"Niu, X., Chen, L., & Chen, Q. (2011). Research on genetic algorithm based on emotion recognition using physiological signals. In: International conference on computational problem-solving I (pp. 614\u2013618), October 21\u201323, 2011, Chengdu, China.","DOI":"10.1109\/ICCPS.2011.6092256"},{"key":"9781_CR23","unstructured":"Olivier Lartillot, P. T. (2007). A matlab toolbox for musical feature extraction from audio. In International conference on digital audio effects, Bordeaux."},{"key":"9781_CR24","volume-title":"Discrete-time signal processing","author":"AV Oppenheim","year":"1999","unstructured":"Oppenheim, A. V., Schafer, R. W., & Buck, J. R. (1999). Discrete-time signal processing. Upper Saddle River, NJ: Prentice Hall."},{"issue":"4","key":"9781_CR25","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1511\/2001.4.344","volume":"89","author":"R Plutchik","year":"2001","unstructured":"Plutchik, R. (2001). The nature of emotions: Human emotions have deep evolutionary roots, a fact that may explain their complexity and provide tools for clinical practice. American Scientist, 89(4), 344\u2013350.","journal-title":"American Scientist"},{"key":"9781_CR26","unstructured":"Prat, C. C. (1950). Music as the language of emotion. The Library of Congress."},{"key":"9781_CR27","volume-title":"Digital processing of speech signals","author":"L Rabiner","year":"1978","unstructured":"Rabiner, L., & Schafer, R. W. (1978). Digital processing of speech signals. Englewood Cliffs, NJ: Prentice-Hall."},{"key":"9781_CR28","unstructured":"Rao, V., Ramakrishnan, S., & Rao, P. (2003). Singing voice detection in North Indian classical music. In National conference on communications, February 01\u201303, 2003, Indian Institute of Technology, Bombay."},{"issue":"5","key":"9781_CR29","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1037\/h0057033","volume":"29","author":"RT Ross","year":"1938","unstructured":"Ross, R. T. (1938). A statistic for circular series. Journal of Educational Psychology, 29(5), 384\u2013389.","journal-title":"Journal of Educational Psychology"},{"issue":"6","key":"9781_CR30","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1037\/h0077714","volume":"39","author":"JA Russell","year":"1980","unstructured":"Russell, J. A. (1980). A circumplex model of affect. Journal of Personality and Social Psychology, 39(6), 1161\u20131178.","journal-title":"Journal of Personality and Social Psychology"},{"issue":"6","key":"9781_CR31","doi-asserted-by":"publisher","first-page":"1802","DOI":"10.1109\/TASL.2010.2101596","volume":"19","author":"P Saari","year":"2011","unstructured":"Saari, P., Eerola, T., & Lartillot, O. (2011). Generalizability and simplicity as criteria in feature selection: Application to mood classification in music. IEEE Transactions on Audio, Speech and Language Processing, 19(6), 1802\u20131812.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9781_CR32","first-page":"1","volume":"3045","author":"R Sawata","year":"2017","unstructured":"Sawata, R., Ogawa, T., & Haseyama, M. (2017). Novel audio feature projection using KDLPCCA-based correlation with EEG features for favorite music classification. IEEE Transactions on Affective Computing, 3045, 1\u201314.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"9781_CR33","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber, J. (2015). Deep learning in neural networks: An overview. Neural Networks, 61, 85\u2013117.","journal-title":"Neural Networks"},{"key":"9781_CR34","doi-asserted-by":"crossref","unstructured":"Shakya, A., Gurung, B., Thapa, M. S., & Rai, M. (2017). Music classification based on genre and mood. In International conference on computational intelligence, communications and bussiness analytics (Vol. 776, pp. 168\u2013183), Singapore.","DOI":"10.1007\/978-981-10-6430-2_14"},{"key":"9781_CR35","volume-title":"The biopsychology of mood and arousal","author":"RE Thayer","year":"1989","unstructured":"Thayer, R. E. (1989). The biopsychology of mood and arousal. New York, NY: Oxford University Press."},{"key":"9781_CR36","doi-asserted-by":"crossref","unstructured":"Tseng, K. C., Lin, B. S., Han, C. M., & Wang, P. S. (2013). Emotion recognition of EEG underlying favourite music by support vector machine. In Proceedings of 1st international conference on Orange technologies, pp. 155\u2013158, March 12\u201316, 2013, Tainan, Taiwan.","DOI":"10.1109\/ICOT.2013.6521181"},{"issue":"2","key":"9781_CR37","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1109\/TASL.2007.913750","volume":"16","author":"D Turnbull","year":"2008","unstructured":"Turnbull, D., Barrington, L., Torres, D., & Lanckriet, G. (2008). Semantic annotation and retrieval of music and sound effects. IEEE Transactions on Audio, Speech and Language Processing, 16(2), 467\u2013476.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"3","key":"9781_CR38","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1017\/S1355771800003071","volume":"4","author":"G Tzanetakis","year":"2000","unstructured":"Tzanetakis, G., & Cook, P. (2000). MARSYAS: A framework for audio analysis. Organised Sound, 4(3), 169\u2013175.","journal-title":"Organised Sound"},{"key":"9781_CR39","unstructured":"Wang, J., Chen, N., & Zhang, K. (2010). Music emotional classification and continuous model. In Proceedings of 2nd international conference on software engineering and data mining (SEDM) (pp. 544\u2013547), June 23\u201325, 2010, Chengdu, China."},{"issue":"1","key":"9781_CR40","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/TAFFC.2015.2397457","volume":"6","author":"JC Wang","year":"2015","unstructured":"Wang, J. C., Yang, Y. H., Wang, H. M., & Jeng, S. K. (2015). Modeling the affective content of music with a Gaussian mixture model. IEEE Transactions on Affective Computing, 6(1), 56\u201368.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"9781_CR41","doi-asserted-by":"crossref","unstructured":"Wang, S. Y., Wang, J. C., Yang, Y. H., & Wang, H. M. (2014). Towards time\u2014Varying music auto-tagging based on CAL500 expansion. In Proceedings of international conference on multimedia and expo., July 14\u201318, 2014, Chengdu, China","DOI":"10.1109\/ICME.2014.6890290"},{"key":"9781_CR42","doi-asserted-by":"crossref","unstructured":"Wei, Z., Li, X., & Yang, L. (2014). Extraction and evaluation model for the basic characteristics of MIDI file music. In Proceedings of 26th Chinese control and decision conference (pp. 2083\u20132087), May 31\u2013June 2, 2014, Changsha, China.","DOI":"10.1109\/CCDC.2014.6852510"},{"issue":"3","key":"9781_CR43","doi-asserted-by":"publisher","first-page":"1845","DOI":"10.1109\/TIT.2017.2776228","volume":"64","author":"T Wiatowski","year":"2018","unstructured":"Wiatowski, T., & Bolcskei, H. (2018). A mathematical theory of deep convolutional neural networks for feature extraction. IEEE Transactions on Information Theory, 64(3), 1845\u20131866.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"3","key":"9781_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2168752.2168754","volume":"3","author":"Y-H Yang","year":"2012","unstructured":"Yang, Y.-H., & Chen, H. H. (2012). Machine recognition of music emotion. ACM Transactions on Intelligent Systems and Technology, 3(3), 1\u201330.","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"9781_CR45","doi-asserted-by":"publisher","DOI":"10.1201\/b10731","volume-title":"Music emotion recognition","author":"YH Yang","year":"2011","unstructured":"Yang, Y. H., Su, Y. F., Lin, Y. C., & Chen, H. H. (2011). Music emotion recognition. Boca Raton: CRC Press."},{"key":"9781_CR46","unstructured":"Zhu, B., & Bai, Z. C. (2010). Overview of artificial emotion in music. In Conference on computer-aided industrial design and conceptual design (Vol. 2, pp. 1577\u20131581), November 17\u201319, 2010, Yiwu, China."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09781-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-020-09781-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09781-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T11:28:58Z","timestamp":1629199738000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-020-09781-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,26]]},"references-count":46,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["9781"],"URL":"https:\/\/doi.org\/10.1007\/s10772-020-09781-0","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,26]]},"assertion":[{"value":"27 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 November 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}