{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T03:27:19Z","timestamp":1768793239676,"version":"3.49.0"},"reference-count":16,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. &amp; Syst."],"published-print":{"date-parts":[[2024,1,1]]},"DOI":"10.1587\/transinf.2023mul0003","type":"journal-article","created":{"date-parts":[[2023,12,31]],"date-time":"2023-12-31T22:39:17Z","timestamp":1704062357000},"page":"49-52","source":"Crossref","is-referenced-by-count":3,"title":["CQTXNet: A Modified Xception Network with Attention Modules for Cover Song Identification"],"prefix":"10.1587","volume":"E107.D","author":[{"given":"Jinsoo","family":"SEO","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Gangneung-Wonju National University"}]},{"given":"Junghyun","family":"KIM","sequence":"additional","affiliation":[{"name":"Content Research Division, Electronics and Telecommunications Research Institute"}]},{"given":"Hyemi","family":"KIM","sequence":"additional","affiliation":[{"name":"Content Research Division, Electronics and Telecommunications Research Institute"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] J. Serra, E. Gomez, P. Herrera, and X. Serra, \u201cChroma binary similarity and local alignment applied to cover song identification,\u201d IEEE Trans. Audio Speech Lang. Process., vol.16, no.6, pp.1138-1151, Aug. 2008. 10.1109\/tasl.2008.924595","DOI":"10.1109\/TASL.2008.924595"},{"key":"2","unstructured":"[2] T. Bertin-Mahieux and D.P.W. Ellis, \u201cLarge-scale cover song recognition using the 2D Fourier transform magnitude,\u201d Proc. ISMIR-2012, pp.241-246, 2012."},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] J.S. Seo, \u201cMulti-scale chroma <i>n<\/i>-gram indexing for cover song identification,\u201d IEICE Trans. Inf. &amp; Syst., vol.E103-D, no.1, pp.59-62, 2020. 10.1587\/transinf.2019mul0001","DOI":"10.1587\/transinf.2019MUL0001"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] X. Xu, X. Chen, and D. Yang, \u201cKey-invariant convolutional neural network toward efficient cover song identification,\u201d Proc. ICME-2018, pp.1-6, 2018. 10.1109\/icme.2018.8486531","DOI":"10.1109\/ICME.2018.8486531"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] F. Yesiler, J. Serr\u00e0, and E. G\u00f3mez, \u201cAccurate and scalable version identification using musically-motivated embeddings,\u201d Proc. ICASSP-2020, pp.21-25, 2020. 10.1109\/icassp40776.2020.9053793","DOI":"10.1109\/ICASSP40776.2020.9053793"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] Z. Yu, X. Xu, X. Chen, and D. Yang, \u201cLearning a representation for cover song identification using convolutional neural network,\u201d Proc. ICASSP-2020, pp.541-545, 2020. 10.1109\/icassp40776.2020.9053839","DOI":"10.1109\/ICASSP40776.2020.9053839"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] F. Chollet, \u201cXception: Deep learning with depthwise separable convolutions,\u201d Proc. CVPR-2017, pp.1251-1258, 2017. 10.1109\/cvpr.2017.195","DOI":"10.1109\/CVPR.2017.195"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d Proc. CVPR-2016, pp.770-778, 2016. 10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, \u201cMobileNetV2: Inverted residuals and linear bottlenecks,\u201d Proc. CVPR-2018, pp.4510-4520, 2018. 10.1109\/cvpr.2018.00474","DOI":"10.1109\/CVPR.2018.00474"},{"key":"10","doi-asserted-by":"publisher","unstructured":"[10] C.Y. Kim, K.S. Um, and S.W. Heo, \u201cA novel MobileNet with selective depth multiplier to compromise complexity and accuracy,\u201d ETRI Journal, vol.45, no.4, pp.666-677, Aug. 2023. 10.4218\/etrij.2022-0103","DOI":"10.4218\/etrij.2022-0103"},{"key":"11","doi-asserted-by":"publisher","unstructured":"[11] Z. Niu, G. Zhong, and H. Yu, \u201cA review on the attention mechanism of deep learning,\u201d Neurocomputing, vol.452, pp.48-62, Sept. 2021. 10.1016\/j.neucom.2021.03.091","DOI":"10.1016\/j.neucom.2021.03.091"},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] J. Hu, L. Shen, S. Albanie, G. Sun, and E. Wu, \u201cSqueeze-and-excitation networks,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.42, no.8, pp.2011-2023, Aug. 2020. 10.1109\/tpami.2019.2913372","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] S. Woo, J. Park, J.-Y. Lee, and I.S. Kweon, \u201cCBAM: Convolutional block attention module,\u201d Proc. ECCV-2018, pp.3-19, 2018. 10.1007\/978-3-030-01234-2_1","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] B. McFee, C. Raffel, D. Liang, D.P.W. Ellis, M. McVicar, E. Battenberg, and O. Nieto, \u201clibrosa: Audio and music signal analysis in python,\u201d Proc. 14th python in science conference, pp.18-25, 2015. 10.25080\/majora-7b98e3ed-003","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] X. Du, Z. Yu, B. Zhu, X. Chen, and Z. Ma, \u201cBytecover: Cover song identification via multi-loss training,\u201d Proc. ICASSP-2021, pp.551-555, 2021. 10.1109\/icassp39728.2021.9414128","DOI":"10.1109\/ICASSP39728.2021.9414128"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] D.P.W. Ellis and G.E. Poliner, \u201cIdentifying \u2018cover songs\u2019 with chroma features and dynamic programming beat tracking,\u201d Proc. ICASSP-2007, pp.1429-1432, 2007. 10.1109\/icassp.2007.367348","DOI":"10.1109\/ICASSP.2007.367348"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/1\/E107.D_2023MUL0003\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T04:15:13Z","timestamp":1704514513000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/1\/E107.D_2023MUL0003\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,1]]},"references-count":16,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2023mul0003","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,1]]},"article-number":"2023MUL0003"}}