{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:28:45Z","timestamp":1740122925651,"version":"3.37.3"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"18","license":[{"start":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T00:00:00Z","timestamp":1622764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T00:00:00Z","timestamp":1622764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100005374","name":"Nanjing University of Posts and Telecommunications","doi-asserted-by":"publisher","award":["No. NY219107"],"award-info":[{"award-number":["No. NY219107"]}],"id":[{"id":"10.13039\/501100005374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["51708299"],"award-info":[{"award-number":["51708299"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s11042-021-11049-x","type":"journal-article","created":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T13:03:07Z","timestamp":1622811787000},"page":"28463-28486","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Pitch contours curve frequency domain fitting with vocabulary matching based music generation"],"prefix":"10.1007","volume":"80","author":[{"given":"Runnan","family":"Lang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songhao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongsheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,6,4]]},"reference":[{"key":"11049_CR1","doi-asserted-by":"crossref","unstructured":"Ammari T, Kaye J, Tsai JY, Bentley F (2019) Music, search, and IoT: how people (really) use voice assistants. ACM Transactions on Computer-Human Interaction (ATOCHI) 26(3):1\u201328","DOI":"10.1145\/3311956"},{"key":"11049_CR2","unstructured":"Bittner RM, Salamon J, Bosch JJ, Bello JP (2017) Pitch contours as a mid-level representation for music informatics. In Audio Engineering Society Conference: 2017 AES International Conference on Semantic Audio. Audio Engineering Society"},{"key":"11049_CR3","doi-asserted-by":"publisher","first-page":"48451","DOI":"10.1109\/ACCESS.2020.2979348","volume":"8","author":"W Cai","year":"2020","unstructured":"Cai W, Wei Z (2020) PiiGAN: generative adversarial networks for pluralistic image inpainting. IEEE Access 8:48451\u201348463","journal-title":"IEEE Access"},{"key":"11049_CR4","unstructured":"Chen CJ (2014) U.S. Patent No. 8,886,539. Washington, DC: U.S. Patent and Trademark Office"},{"key":"11049_CR5","doi-asserted-by":"crossref","unstructured":"Chen K, Zhang W, Dubnov S, Xia G, Li W (2019) The effect of explicit structure encoding of deep neural networks for symbolic music generation. In 2019 International Workshop on Multilayer Music Representation and Processing (MMRP), 77-84","DOI":"10.1109\/MMRP.2019.00022"},{"key":"11049_CR6","unstructured":"Conklin D (2003) Music generation from statistical models. In Proceedings of the AISB 2003 Symposium on Artificial Intelligence and Creativity in the Arts and Sciences, 30-35"},{"issue":"90","key":"11049_CR7","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1090\/S0025-5718-1965-0178586-1","volume":"19","author":"JW Cooley","year":"1965","unstructured":"Cooley JW, Tukey JW (1965) An algorithm for the machine calculation of complex Fourier series. Math Comput 19(90):297\u2013301","journal-title":"Math Comput"},{"key":"11049_CR8","doi-asserted-by":"crossref","unstructured":"Dong HW, Hsiao WY, Yang LC, Yang YH (2018) Musegan: multi-track sequential generative adversarial networks for symbolic music generation and accompaniment. In Thirty-Second AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v32i1.11312"},{"key":"11049_CR9","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, \u22ef, Bengio Y (2014) Generative adversarial nets. In Advances in neural information processing systems, 2672\u20132680"},{"key":"11049_CR10","doi-asserted-by":"crossref","unstructured":"Hadjeres G, Nielsen F, Pachet F (2017) GLSR-VAE: Geodesic latent space regularization for variational autoencoder architectures. In 2017 IEEE Symposium Series on Computational Intelligence (SSCI), 1\u20137","DOI":"10.1109\/SSCI.2017.8280895"},{"key":"11049_CR11","unstructured":"Hiller LA, Isaacson LM (1959) Experimental Music: Composition with an Electronic Computer. McGraw-Hill Publishing Company, London"},{"issue":"8","key":"11049_CR12","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 (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"11049_CR13","doi-asserted-by":"crossref","unstructured":"Hsieh TH, Su L, Yang YH (2019) A streamlined encoder\/decoder architecture for melody extraction. In ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 156\u2013160","DOI":"10.1109\/ICASSP.2019.8682389"},{"key":"11049_CR14","doi-asserted-by":"crossref","unstructured":"Jeon W, Ma C (2011) Efficient search of music pitch contours using wavelet transforms and segmented dynamic time warping. In 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2304\u20132307","DOI":"10.1109\/ICASSP.2011.5946943"},{"key":"11049_CR15","doi-asserted-by":"crossref","unstructured":"Jiang J, Xia GG, Carlton DB, Anderson CN, Miyakawa RH (2020) Transformer VAE: a hierarchical model for structure-aware and interpretable music representation learning. In ICASSP 2020\u2013-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 516\u2013520","DOI":"10.1109\/ICASSP40776.2020.9054554"},{"key":"11049_CR16","unstructured":"Keerti G, Vaishnavi AN, Mukherjee P, Vidya AS, Sreenithya GS, Nayab D (2020) Attentional networks for music generation. arXiv preprint arXiv:2002.03854"},{"key":"11049_CR17","unstructured":"Lim H, Rhyu S, Lee K (2017) Chord generation from symbolic melody using BLSTM networks. arXiv preprint arXiv:1712.01011"},{"key":"11049_CR18","doi-asserted-by":"crossref","unstructured":"Mangal S, Modak R, Joshi P (2019) LSTM based music generation system. arXiv preprint arXiv:1908.01080","DOI":"10.17148\/IARJSET.2019.6508"},{"key":"11049_CR19","doi-asserted-by":"crossref","unstructured":"Ouyang P, Yin S, Wei S (2017) A fast and power efficient architecture to parallelize LSTM based RNN for cognitive intelligence applications. In Proceedings of the 54th Annual Design Automation Conference 2017, 1-6","DOI":"10.1145\/3061639.3062187"},{"key":"11049_CR20","unstructured":"Razavi A, van den Oord A, Vinyals O (2019) Generating diverse high-fidelity images with vq-vae-2. In 2019 Conference on Neural Information Processing Systems (NIPS):14837\u201314847\u201314847"},{"issue":"6","key":"11049_CR21","doi-asserted-by":"publisher","first-page":"1759","DOI":"10.1109\/TASL.2012.2188515","volume":"20","author":"J Salamon","year":"2012","unstructured":"Salamon J, G\u00f3mez E (2012) Melody extraction from polyphonic music signals using pitch contour characteristics. IEEE Trans Audio Speech Lang Process 20(6):1759\u20131770","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"11049_CR22","unstructured":"Salamon J, Peeters G, R\u00f6bel A (2012) Statistical characterisation of melodic pitch contours and its application for melody extraction. In ISMIR, 187\u2013192"},{"key":"11049_CR23","doi-asserted-by":"publisher","first-page":"71353","DOI":"10.1109\/ACCESS.2020.2986267","volume":"8","author":"Z Wang","year":"2020","unstructured":"Wang Z, Zou C, Cai W (2020) Small sample classification of hyperspectral remote sensing images based on sequential joint Deeping learning model. IEEE Access 8:71353\u201371363","journal-title":"IEEE Access"},{"key":"11049_CR24","doi-asserted-by":"crossref","unstructured":"Wu J, Hu C, Wang Y, Hu X, Zhu J (2019) A hierarchical recurrent neural network for symbolic melody generation. IEEE Transactions on Cybernetics\u00a050(6):2749\u20132757","DOI":"10.1109\/TCYB.2019.2953194"},{"key":"11049_CR25","unstructured":"Yamshchikov IP, Tikhonov A (2017) Music generation with variational recurrent autoencoder supported by history. arXiv preprint arXiv:1705.05458"},{"key":"11049_CR26","unstructured":"Yang LC, Chou SY, Yang YH (2017) MidiNet: a convolutional generative adversarial network for symbolic-domain music generation. arXiv preprint arXiv:1703.10847"},{"issue":"2","key":"11049_CR27","doi-asserted-by":"publisher","first-page":"1281","DOI":"10.1109\/TGRS.2019.2945591","volume":"58","author":"H You","year":"2019","unstructured":"You H, Tian S, Yu L, Lv Y (2019) Pixel-level remote sensing image recognition based on bidirectional word vectors. IEEE Trans Geosci Remote Sens 58(2):1281\u20131293","journal-title":"IEEE Trans Geosci Remote Sens"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11049-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11049-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11049-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T21:55:33Z","timestamp":1672350933000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11049-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,4]]},"references-count":27,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["11049"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11049-x","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2021,6,4]]},"assertion":[{"value":"26 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 November 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 May 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}