{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T12:10:02Z","timestamp":1732536602911,"version":"3.28.0"},"reference-count":55,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2024,8,1]]},"DOI":"10.1587\/transinf.2023edp7044","type":"journal-article","created":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T22:17:00Z","timestamp":1722464220000},"page":"1079-1088","source":"Crossref","is-referenced-by-count":0,"title":["MDX-Mixer: Music Demixing by Leveraging Source Signals Separated by Existing Demixing Models"],"prefix":"10.1587","volume":"E107.D","author":[{"given":"Tomoyasu","family":"NAKANO","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masataka","family":"GOTO","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] J. Woodruff, B. Pardo, and R. Dannenberg, \u201cRemixing stereo music with score-informed source separation,\u201d Proc. 7th Int. Conf. Music Information Retrieval (ISMIR 2006), pp.314-319, 2006. 10.5281\/zenodo.1414898"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] O. Gillet and G. Richard, \u201cExtraction and remixing of drum tracks from polyphonic music signals,\u201d Proc. 2005 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2005), pp.315-318, 2005. 10.1109\/ASPAA.2005.1540232","DOI":"10.1109\/ASPAA.2005.1540232"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] K. Yoshii, M. Goto, and H.G. Okuno, \u201cINTER:D: A drum sound equalizer for controlling volume and timbre of drums,\u201d Proc. 2nd European Workshop on the Integration of Knowledge, Semantic and Digital Media Technologies (EWIMT 2005), pp.205-212, 2005.","DOI":"10.1049\/ic.2005.0733"},{"key":"4","unstructured":"[4] K. Itoyama, M. Goto, K. Komatani, T. Ogata, and H.G. Okuno, \u201cInstrument equalizer for query-by-example retrieval: Improving sound source separation based on integrated harmonic and inharmonic models,\u201d Proc. 9th Int. Conf. Music Information Retrieval (ISMIR 2008), pp.133-138, 2008. 10.5281\/zenodo.1417407"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] J. Pons, J. Janer, T. Rode, and W. Nogueira, \u201cRemixing music using source separation algorithms to improve the musical experience of cochlear implant users,\u201d The J. the Acoustical Society of America, vol.140, no.6, pp.4338-4349, 2016. 10.1121\/1.4971424","DOI":"10.1121\/1.4971424"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] Y. Ren, X. Tan, T. Qin, J. Luan, Z. Zhao, and T.-Y. Liu, \u201cDeepSinger: Singing voice synthesis with data mined from the web,\u201d Proc. 2020 ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD 2020), pp.1979-1989, 2020. 10.1145\/3394486.3403249","DOI":"10.1145\/3394486.3403249"},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] H. Yakura, K. Watanabe, and M. Goto, \u201cSelf-supervised contrastive learning for singing voices,\u201d IEEE\/ACM Trans. Audio Speech and Language Processing, vol.30, pp.1614-1623, 2022. 10.1109\/taslp.2022.3169627","DOI":"10.1109\/TASLP.2022.3169627"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] B. Sharma, R.K. Das, and H. Li, \u201cOn the importance of audio-source separation for singer identification in polyphonic music,\u201d Proc. 20th Annual Conference of the International Speech Communication Association (Interspeech 2019), pp.2020-2024, 2019.","DOI":"10.21437\/Interspeech.2019-1925"},{"key":"9","doi-asserted-by":"publisher","unstructured":"[9] T. Nakatsuka, K. Watanabe, Y. Koyama, M. Hamasaki, M. Goto, and S. Morishima, \u201cVocal-accompaniment compatibility estimation using self-supervised and joint-embedding techniques,\u201d IEEE Access, vol.9, pp.101994-102003, 2021. 10.1109\/access.2021.3096819","DOI":"10.1109\/ACCESS.2021.3096819"},{"key":"10","doi-asserted-by":"publisher","unstructured":"[10] Z. Rafii, A. Liutkus, F.-R. St\u00f6ter, S.I. Mimilakis, D. FitzGerald, and B. Pardo, \u201cAn overview of lead and accompaniment separation in music,\u201d IEEE\/ACM Trans. Audio Speech and Language Processing, vol.26, no.8, pp.1307-1335, 2018. 10.1109\/taslp.2018.2825440","DOI":"10.1109\/TASLP.2018.2825440"},{"key":"11","doi-asserted-by":"publisher","unstructured":"[11] C. Gupta, H. Li, and M. Goto, \u201cDeep learning approaches in topics of singing information processing,\u201d IEEE\/ACM Trans. Audio Speech and Language Processing, vol.30, pp.2422-2451, 2022. 10.1109\/taslp.2022.3190732","DOI":"10.1109\/TASLP.2022.3190732"},{"key":"12","unstructured":"[12] A. Jansson, E. Humphrey, N. Montecchio, R. Bittner, A. Kumar, and T. Weyde, \u201cSinging voice separation with deep U-Net convolutional networks,\u201d Proc. 18th International Society for Music Information Retrieval Conference (ISMIR 2017), pp.745-751, 2017. 10.5281\/zenodo.1414934"},{"key":"13","doi-asserted-by":"publisher","unstructured":"[13] F.-R. St\u00f6ter, S. Uhlich, A. Liutkus, and Y. Mitsufuji, \u201cOpen-Unmix-a reference implementation for music source separation,\u201d J. Open Source Software, vol.4, no.41, p.1667, 2019. 10.21105\/joss.01667","DOI":"10.21105\/joss.01667"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] N. Takahashi, N. Goswami, and Y. Mitsufuji, \u201cMMDenseLSTM: An efficient combination of convolutional and recurrent neural networks for audio source separation,\u201d Proc. 16th International Workshop on Acoustic Signal Enhancement (IWAENC 2018), pp.106-110, 2018.","DOI":"10.1109\/IWAENC.2018.8521383"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] A. Jansson, R.M. Bittner, S. Ewert, and T. Weyde, \u201cJoint singing voice separation and F0 estimation with deep U-Net architectures,\u201d Proc. 27th European Signal Processing Conference (EUSIPCO 2019), pp.1-5, 2019. 10.23919\/EUSIPCO.2019.8902550","DOI":"10.23919\/EUSIPCO.2019.8902550"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] T. Nakano, K. Yoshii, Y. Wu, R. Nishikimi, K.W.E. Lin, and M. Goto, \u201cJoint singing pitch estimation and voice separation based on a neural harmonic structure renderer,\u201d Proc. 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2019), pp.155-159, 2019. 10.1109\/WASPAA.2019.8937135","DOI":"10.1109\/WASPAA.2019.8937135"},{"key":"17","unstructured":"[17] Y.N. Hung and A. Lerch, \u201cMultitask learning for instrument activation aware music source separation,\u201d Proc. 21st International Society for Music Information Retrieval Conference (ISMIR 2020), pp.748-755, 2020. 10.5281\/zenodo.4245548"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] R. Sawata, S. Uhlich, S. Takahashi, and Y. Mitsufuji, \u201cAll for one and one for all: Improving music separation by bridging networks,\u201d Proc. 46th IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP 2021), pp.51-55, 2021. 10.1109\/ICASSP39728.2021.9414044","DOI":"10.1109\/ICASSP39728.2021.9414044"},{"key":"19","unstructured":"[19] N. Takahashi and Y. Mitsufuji, \u201cD3Net: Densely connected multidilated densenet for music source separation,\u201d Proc. 2021 Conference on Computer Vision and Pattern Recognition (CVPR 2021), pp.993-1002, 2021."},{"key":"20","doi-asserted-by":"publisher","unstructured":"[20] R. Hennequin, A. Khlif, F. Voituret, and M. Moussallam, \u201cSpleeter: A fast and efficient music source separation tool with pre-trained models,\u201d J. Open Source Software, vol.5, no.50, p.2154, 2020. 10.21105\/joss.02154","DOI":"10.21105\/joss.02154"},{"key":"21","doi-asserted-by":"publisher","unstructured":"[21] K. Schulze-Forster, C.S.J. Doire, G. Richard, and R. Badeau, \u201cPhoneme level lyrics alignment and text-informed singing voice separation,\u201d IEEE\/ACM Trans. Audio Speech and Language Processing, vol.29, pp.2382-2395, 2021. 10.1109\/taslp.2021.3091817","DOI":"10.1109\/TASLP.2021.3091817"},{"key":"22","unstructured":"[22] W. Choi, M. Kim, J. Chung, D. Lee, and S. Jung, \u201cInvestigating U-Nets with various intermediate blocks for spectrogram-based singing voice separation,\u201d Proc. 21st International Society for Music Information Retrieval Conference (ISMIR 2020), pp.192-198, 2020."},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] W. Choi, M. Kim, J. Chung, and S. Jung, \u201cLaSAFT: Latent source attentive frequency transformation for conditioned source separation,\u201d Proc. 46th IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP 2021), pp.171-175, 2021. 10.1109\/ICASSP39728.2021.9413896","DOI":"10.1109\/ICASSP39728.2021.9413896"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] Z. Wang, R. Giri, U. Isik, J.-M. Valin, and A. Krishnaswamy, \u201cSemi-supervised singing voice separation with noisy self-training,\u201d Proc. 46th IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP 2021), 2021. 10.1109\/ICASSP39728.2021.9413723","DOI":"10.1109\/ICASSP39728.2021.9413723"},{"key":"25","unstructured":"[25] Q. Kong, Y. Cao, H. Liu, K. Cho, and Y. Wang, \u201cDecoupling magnitude and phase estimation with deep ResUNet for music source separation,\u201d Proc. 22nd International Society for Music Information Retrieval Conference (ISMIR 2021), pp.342-349, 2021."},{"key":"26","unstructured":"[26] D. St\u00f6ller, S. Ewert, and S. Dixon, \u201cWave-U-Net: A multi-scale neural network for end-to-end audio source separation,\u201d Proc. 18th International Society for Music Information Retrieval Conference (ISMIR 2017), pp.330-340, 2017."},{"key":"27","doi-asserted-by":"publisher","unstructured":"[27] Y. Luo and N. Mesgarani, \u201cConv-TasNet: Surpassing ideal time-frequency magnitude masking for speech separation,\u201d IEEE\/ACM Trans. Audio Speech and Language Processing, vol.27, no.8, pp.1256-1266, 2019. 10.1109\/taslp.2019.2915167","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] T. Nakamura and H. Saruwatari, \u201cTime-domain audio source separation based on Wave-U-Net combined with discrete wavelet transform,\u201d Proc. 45th IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP 2020), pp.386-390, 2020. 10.1109\/ICASSP40776.2020.9053934","DOI":"10.1109\/ICASSP40776.2020.9053934"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] D. Samuel, A. Ganeshan, and J. Naradowsky, \u201cMeta-learning extractors for music source separation,\u201d Proc. 45th IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP 2020), pp.816-820, 2020. 10.1109\/ICASSP40776.2020.9053513","DOI":"10.1109\/ICASSP40776.2020.9053513"},{"key":"30","unstructured":"[30] E. Nachmani, Y. Adi, and L. Wolf, \u201cVoice separation with an unknown number of multiple speakers,\u201d Proc. 37th Int. Conf. Machine Learning (ICML 2020), pp.7164-7175, 2020."},{"key":"31","unstructured":"[31] M. Kim, W. Choi, J. Chung, D. Lee, and S. Jung, \u201cKUIELab-MDX-Net: A two-stream neural network for music demixing,\u201d Proc. Music Demixing Workshop 2021 (MDX 2021), pp.1-7, 2021."},{"key":"32","unstructured":"[32] A. D\u00e9fossez, \u201cHybrid spectrogram and waveform source separation,\u201d Proc. Music Demixing Workshop 2021 (MDX 2021), pp.1-11, 2021."},{"key":"33","doi-asserted-by":"publisher","unstructured":"[33] Y. Hu, Y. Chen, W. Yang, L. He, and H. Huang, \u201cHierarchic temporal convolutional network with cross-domain encoder for music source separation,\u201d IEEE Signal Processing Letters, vol.29, pp.1517-1521, 2022. 10.1109\/lsp.2022.3187316","DOI":"10.1109\/LSP.2022.3187316"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] L. Pr\u00e9tet, R. Hennequin, J. Royo-Letelier, and A. Vaglio, \u201cSinging voice separation: A study on training data,\u201d Proc. 44th IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP 2019), pp.506-510, 2019. 10.1109\/ICASSP.2019.8683555","DOI":"10.1109\/ICASSP.2019.8683555"},{"key":"35","doi-asserted-by":"crossref","unstructured":"[35] A. Cohen-Hadria, A. Roebel, and G. Peeters, \u201cImproving singing voice separation using Deep U-Net and Wave-U-Net with data augmentation,\u201d Proc. 27th European Signal Processing Conference (EUSIPCO 2019), pp.1-5, 2019. 10.23919\/EUSIPCO.2019.8902810","DOI":"10.23919\/EUSIPCO.2019.8902810"},{"key":"36","doi-asserted-by":"crossref","unstructured":"[36] Y. Wang, D. Stoller, R.M. Bittner, and J.P. Bello, \u201cFew-shot musical source separation,\u201d Proc. 47th IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP 2022), pp.121-125, 2022. 10.1109\/ICASSP43922.2022.9747536","DOI":"10.1109\/ICASSP43922.2022.9747536"},{"key":"37","doi-asserted-by":"crossref","unstructured":"[37] M. Kawamura, T. Nakamura, D. Kitamura, H. Saruwatari, Y. Takahashi, and K. Kondo, \u201cDifferentiable digital signal processing mixture model for synthesis parameter extraction from mixture of harmonic sounds,\u201d Proc. 47th IEEE 2022 Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP 2022), pp.941-945, 2022. 10.1109\/ICASSP43922.2022.9746399","DOI":"10.1109\/ICASSP43922.2022.9746399"},{"key":"38","unstructured":"[38] Z. Rafii, A. Liutkus, F.-R. St\u00f6ter, S.I. Mimilakis, and R. Bittner, \u201cThe MUSDB18 corpus for music separation.\u201d https:\/\/doi.org\/10.5281\/zenodo.1117372. 10.5281\/zenodo.1117372"},{"key":"39","unstructured":"[39] Z. Rafii, A. Liutkus, F.-R. St\u00f6ter, S.I. Mimilakis, and R. Bittner, \u201cMUSDB18-HQ-an uncompressed version of MUSDB18.\u201d https:\/\/doi.org\/10.5281\/zenodo.3338373. 10.5281\/zenodo.3338373"},{"key":"40","doi-asserted-by":"crossref","unstructured":"[40] S. Uhlich, M. Porcu, F. Giron, M. Enenkl, T. Kemp, N. Takahashi, and Y. Mitsufuji, \u201cImproving music source separation based on deep neural networks through data augmentation and network blending,\u201d Proc. 42nd IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP 2017), pp.261-265, 2017. 10.1109\/ICASSP.2017.7952158","DOI":"10.1109\/ICASSP.2017.7952158"},{"key":"41","doi-asserted-by":"publisher","unstructured":"[41] X. Jaureguiberry, E. Vincent, and G. Richard, \u201cFusion methods for speech enhancement and audio source separation,\u201d IEEE Trans. Audio Speech and Language Processing, vol.24, no.7, pp.1266-1279, 2016. 10.1109\/taslp.2016.2553441","DOI":"10.1109\/TASLP.2016.2553441"},{"key":"42","doi-asserted-by":"crossref","unstructured":"[42] J.L. Roux, S. Watanabe, and J.R. Hershey, \u201cEnsemble learning for speech enhancement,\u201d Proc. 23rd IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2013), pp.1-4, 2013. 10.1109\/WASPAA.2013.6701888","DOI":"10.1109\/WASPAA.2013.6701888"},{"key":"43","doi-asserted-by":"crossref","unstructured":"[43] W. Jiang, S. Liang, L. Dong, H. Yang, W. Liu, and Y. Wang, \u201cCross-domain cooperative deep stacking network for speech separation,\u201d Proc. 40th IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP 2015), pp.5083-5087, 2015. 10.1109\/ICASSP.2015.7178939","DOI":"10.1109\/ICASSP.2015.7178939"},{"key":"44","doi-asserted-by":"crossref","unstructured":"[44] J. Driedger and M. M\u00fcller, \u201cExtracting singing voice from music recordings by cascading audio decomposition techniques,\u201d Proc. 40th IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP 2015), pp.126-130, 2015. 10.1109\/ICASSP.2015.7177945","DOI":"10.1109\/ICASSP.2015.7177945"},{"key":"45","doi-asserted-by":"crossref","unstructured":"[45] E.M. Grais, G. Roma, A.J.R. Simpson, and M.D. Plumbley, \u201cCombining mask estimates for single channel audio source separation using deep neural networks,\u201d Proc. 17th Annual Conference of the International Speech Communication (Interspeech 2016), pp.3339-3343, 2016.","DOI":"10.21437\/Interspeech.2016-216"},{"key":"46","doi-asserted-by":"publisher","unstructured":"[46] X.-L. Zhang and D.L. Wang, \u201cA deep ensemble learning method for monaural speech separation,\u201d IEEE Trans. Audio, Speech and Language Processing, vol.24, no.5, pp.967-977, 2016. 10.1109\/taslp.2016.2536478","DOI":"10.1109\/TASLP.2016.2536478"},{"key":"47","doi-asserted-by":"crossref","unstructured":"[47] M. McVicar, R. Santos-Rodriguez, and T.D. Bie, \u201cLearning to separate vocals from polyphonic mixtures via ensemble methods and structured output prediction,\u201d Proc. 41st IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP 2016), pp.450-454, 2016. 10.1109\/ICASSP.2016.7471715","DOI":"10.1109\/ICASSP.2016.7471715"},{"key":"48","doi-asserted-by":"crossref","unstructured":"[48] E. Manilow, P. Seetharaman, F. Pishdadian, and B. Pardo, \u201cPredicting algorithm efficacy for adaptive multi-cue source separation,\u201d Proc. IEEE WASPA 2017, pp.274-278, 2017. 10.1109\/WASPAA.2017.8170038","DOI":"10.1109\/WASPAA.2017.8170038"},{"key":"49","unstructured":"[49] A. D\u00e9fossez, N. Usunier, L. Bottou, and F. Bach, \u201cMusic source separation in the waveform domain,\u201d CoRR, arXiv:1911.13254, pp.1-16, 2021. 10.48550\/arXiv.1911.13254"},{"key":"50","doi-asserted-by":"crossref","unstructured":"[50] Y. Mitsufuji, G. Fabbro, S. Uhlich, F.-R. St\u00f6ter, A. D\u00e9fossez, M. Kim, W. Choi, C.-Y. Yu, and K.-W. Cheuk, \u201cMusic demixing challenge 2021,\u201d Proc. Music Demixing Workshop 2021 (MDX 2021), pp.1-8, 2021.","DOI":"10.3389\/frsip.2021.808395"},{"key":"51","unstructured":"[51] I.O. Tolstikhin, N. Houlsby, A. Kolesnikov, L. Beyer, X. Zhai, T. Unterthiner, J. Yung, A. Steiner, D. Keysers, J. Uszkoreit, M. Lucic, and A. Dosovitskiy, \u201cMLP-Mixer: An all-MLP architecture for vision,\u201d Proc. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), pp.24261-24272, 2021."},{"key":"52","unstructured":"[52] J.L. Ba, J.R. Kiros, and G.E. Hinton, \u201cLayer normalization,\u201d CoRR, arXiv:1607.06450, pp.1-14, 2016. 10.48550\/arXiv.1607.06450"},{"key":"53","unstructured":"[53] D. Hendrycks and K. Gimpel, \u201cGaussian error linear units (GELUs),\u201d CoRR, arXiv:1606.08415, pp.1-9, 2016. 10.48550\/arXiv.1606.08415"},{"key":"54","doi-asserted-by":"crossref","unstructured":"[54] J. Tae, H. Kim, and Y. Lee, \u201cMLP Singer: Towards rapid parallel korean singing voice synthesis,\u201d Proc. 2021 IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2021), pp.1-6, 2021. 10.1109\/MLSP52302.2021.9596184","DOI":"10.1109\/MLSP52302.2021.9596184"},{"key":"55","unstructured":"[55] D.P. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d Proc. 3rd Int. Conf. Learning Representations (ICLR 2015), pp.1-15, 2015."}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/8\/E107.D_2023EDP7044\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T11:31:28Z","timestamp":1732534288000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/8\/E107.D_2023EDP7044\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,1]]},"references-count":55,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2023edp7044","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2024,8,1]]},"article-number":"2023EDP7044"}}