{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:25:13Z","timestamp":1750220713924,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,3,17]],"date-time":"2020-03-17T00:00:00Z","timestamp":1584403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"JST ACCEL","award":["JPMJAC1602"],"award-info":[{"award-number":["JPMJAC1602"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,3,17]]},"DOI":"10.1145\/3377325.3377539","type":"proceedings-article","created":{"date-parts":[[2020,3,4]],"date-time":"2020-03-04T23:14:49Z","timestamp":1583363689000},"page":"78-82","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Interactive deep singing-voice separation based on human-in-the-loop adaptation"],"prefix":"10.1145","author":[{"given":"Tomoyasu","family":"Nakano","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Koyama","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masahiro","family":"Hamasaki","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masataka","family":"Goto","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,3,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v35i4.2513"},{"key":"e_1_3_2_1_2_1","volume-title":"ISMIR","author":"Bittner R.","year":"2017","unstructured":"R. Bittner , B. McFee , J. Salamon , P. Li , and J. P. Bello . 2017. Deep Salience Representations for F0 Estimation in Polyphonic Music . In ISMIR 2017 . 63--70. R. Bittner, B. McFee, J. Salamon, P. Li, and J. P. Bello. 2017. Deep Salience Representations for F0 Estimation in Polyphonic Music. In ISMIR 2017. 63--70."},{"key":"e_1_3_2_1_3_1","first-page":"155","article-title":"MedleyDB","volume":"2014","author":"Bittner R. M.","year":"2014","unstructured":"R. M. Bittner , J. Salamon , M. Tierney , M. Mauch , C. Cannam , and J. P. Bello . 2014 . MedleyDB : A Multitrack Dataset for Annotation-Intensive MIR Research. In ISMIR 2014. 155 -- 160 . R. M. Bittner, J. Salamon, M. Tierney, M. Mauch, C. Cannam, and J. P. Bello. 2014. MedleyDB: A Multitrack Dataset for Annotation-Intensive MIR Research. In ISMIR 2014. 155--160.","journal-title":"A Multitrack Dataset for Annotation-Intensive MIR Research. In ISMIR"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557253"},{"volume-title":"AEC Conference.","author":"Caba\u00f1as-Molero P.","key":"e_1_3_2_1_5_1","unstructured":"P. Caba\u00f1as-Molero , D. Mart\u00ednez Mu\u00f1oz , M. Cobos , and J. J. L\u00f3pez . 2011. Singing Voice Separation from Stereo Recordings using Spatial Clues and Robust F0 Estimation . In AEC Conference. P. Caba\u00f1as-Molero, D. Mart\u00ednez Mu\u00f1oz, M. Cobos, and J. J. L\u00f3pez. 2011. Singing Voice Separation from Stereo Recordings using Spatial Clues and Robust F0 Estimation. In AEC Conference."},{"key":"e_1_3_2_1_6_1","volume-title":"Vocals in Music Matter: the Relevance of Vocals in the Minds of Listeners. In ISMIR","author":"Demetriou A.","year":"2018","unstructured":"A. Demetriou , A. Jansson , A. Kumar , and R. M. Bittner . 2018 . Vocals in Music Matter: the Relevance of Vocals in the Minds of Listeners. In ISMIR 2018 . 514--520. A. Demetriou, A. Jansson, A. Kumar, and R. M. Bittner. 2018. Vocals in Music Matter: the Relevance of Vocals in the Minds of Listeners. In ISMIR 2018. 514--520."},{"key":"e_1_3_2_1_7_1","volume-title":"ICASSP","author":"Duong N. Q. K.","year":"2014","unstructured":"N. Q. K. Duong , A. Ozerov , L. Chevallier , and J. Sirot . 2014. An Interactive Audio Source Separation Framework based on Non-negative Matrix Factorization . In ICASSP 2014 . N. Q. K. Duong, A. Ozerov, L. Chevallier, and J. Sirot. 2014. An Interactive Audio Source Separation Framework based on Non-negative Matrix Factorization. In ICASSP 2014."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2158801"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28551-6_54"},{"key":"e_1_3_2_1_10_1","volume-title":"Interactive Machine Learning. In ACM IUI","author":"Fails J. A.","year":"2003","unstructured":"J. A. Fails and Jr. D. R. Olsen . 2003 . Interactive Machine Learning. In ACM IUI 2003. J. A. Fails and Jr. D. R. Olsen. 2003. Interactive Machine Learning. In ACM IUI 2003."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Z. C. Fan J. S. R. Jang and C. L. Lu. 2016. Singing Voice Separation and Pitch Extraction from Monaural Polyphonic Audio Music via DNN and Adaptive Pitch Tracking. In BigMM 2016. 178--185.  Z. C. Fan J. S. R. Jang and C. L. Lu. 2016. Singing Voice Separation and Pitch Extraction from Monaural Polyphonic Audio Music via DNN and Adaptive Pitch Tracking. In BigMM 2016. 178--185.","DOI":"10.1109\/BigMM.2016.56"},{"key":"e_1_3_2_1_12_1","volume-title":"EUSIPCO","author":"Fuentes B.","year":"2012","unstructured":"B. Fuentes , R. Badeau , and G. Richard . 2012. Blind Harmonic Adaptive Decomposition Applied to Supervised Source Separation . In EUSIPCO 2012 . B. Fuentes, R. Badeau, and G. Richard. 2012. Blind Harmonic Adaptive Decomposition Applied to Supervised Source Separation. In EUSIPCO 2012."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041386"},{"key":"e_1_3_2_1_14_1","volume-title":"ISMIR","author":"Goto M.","year":"2002","unstructured":"M. Goto , H. Hashiguchi , T. Nishimura , and R. Oka . 2002. RWC Music Database: Popular, Classical, and Jazz Music Databases . In ISMIR 2002 . 287--288. M. Goto, H. Hashiguchi, T. Nishimura, and R. Oka. 2002. RWC Music Database: Popular, Classical, and Jazz Music Databases. In ISMIR 2002. 287--288."},{"key":"e_1_3_2_1_15_1","first-page":"1482","article-title":"A Tandem Algorithm for Singing Pitch Extraction and Voice Separation From Music Accompaniment","volume":"20","author":"Hsu C. L.","year":"2012","unstructured":"C. L. Hsu , D. Wang , J. R. Jang , and K. Hu . 2012 . A Tandem Algorithm for Singing Pitch Extraction and Voice Separation From Music Accompaniment . IEEE Trans. Acoust., Speech, Signal Process. 20 , 5 (2012), 1482 -- 1491 . C. L. Hsu, D. Wang, J. R. Jang, and K. Hu. 2012. A Tandem Algorithm for Singing Pitch Extraction and Voice Separation From Music Accompaniment. IEEE Trans. Acoust., Speech, Signal Process. 20, 5 (2012), 1482--1491.","journal-title":"IEEE Trans. Acoust., Speech, Signal Process."},{"key":"e_1_3_2_1_16_1","volume-title":"ISMIR","author":"Huang P. S.","year":"2014","unstructured":"P. S. Huang , M. Kim , M. Hasegawa-Johnson , and P. Smaragdis . 2014. Singing-voice Separation from Monaural Recordings using Deep Recurrent Neural Networks . In ISMIR 2014 . 477--482. P. S. Huang, M. Kim, M. Hasegawa-Johnson, and P. Smaragdis. 2014. Singing-voice Separation from Monaural Recordings using Deep Recurrent Neural Networks. In ISMIR 2014. 477--482."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2875133"},{"key":"e_1_3_2_1_18_1","volume-title":"EUSIPCO","author":"Jansson A.","year":"2019","unstructured":"A. Jansson , R. M. Bittner , S. Ewert , and T. Weyde . 2019. Joint Singing Voice Separation and F0 Estimation with Deep U-Net Architectures . In EUSIPCO 2019 . A. Jansson, R. M. Bittner, S. Ewert, and T. Weyde. 2019. Joint Singing Voice Separation and F0 Estimation with Deep U-Net Architectures. In EUSIPCO 2019."},{"key":"e_1_3_2_1_19_1","volume-title":"Singing Voice Separation with Deep U-Net Convolutional Networks. In ISMIR","author":"Jansson A.","year":"2017","unstructured":"A. Jansson , E. J. Humphrey , N. Montecchio , R. Bittner , A. Kumar , and T. Weyde . 2017 . Singing Voice Separation with Deep U-Net Convolutional Networks. In ISMIR 2017 . 745--751. A. Jansson, E. J. Humphrey, N. Montecchio, R. Bittner, A. Kumar, and T. Weyde. 2017. Singing Voice Separation with Deep U-Net Convolutional Networks. In ISMIR 2017. 745--751."},{"key":"e_1_3_2_1_20_1","volume-title":"TextAlive: Integrated Design Environment for Kinetic Typography. In ACM CHI","author":"Kato J.","year":"2015","unstructured":"J. Kato , T. Nakano , and M. Goto . 2015 . TextAlive: Integrated Design Environment for Kinetic Typography. In ACM CHI 2015 . J. Kato, T. Nakano, and M. Goto. 2015. TextAlive: Integrated Design Environment for Kinetic Typography. In ACM CHI 2015."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"B. Kim and B. Pardo. 2018. A Human-in-the-Loop System for Sound Event Detection and Annotation. TiiS 8 2 (2018) 13:1--13:23.  B. Kim and B. Pardo. 2018. A Human-in-the-Loop System for Sound Event Detection and Annotation. TiiS 8 2 (2018) 13:1--13:23.","DOI":"10.1145\/3214366"},{"key":"e_1_3_2_1_22_1","volume-title":"Semi-supervised NMF with Time-frequency Annotations for Single-channel Source Separation. In ISMIR","author":"Lefevre A.","year":"2012","unstructured":"A. Lefevre , F. Bach , and C. Fevotte . 2012 . Semi-supervised NMF with Time-frequency Annotations for Single-channel Source Separation. In ISMIR 2012 . A. Lefevre, F. Bach, and C. Fevotte. 2012. Semi-supervised NMF with Time-frequency Annotations for Single-channel Source Separation. In ISMIR 2012."},{"key":"e_1_3_2_1_23_1","unstructured":"K. W. E. Lin B. T. Balamurali E. K. S. L. and D. Herremans. 2018. Singing Voice Separation using a Deep Convolutional Neural Network Trained by Ideal Binary Mask and Cross Entropy. Neural Computing and Applications (2018) 1--14.  K. W. E. Lin B. T. Balamurali E. K. S. L. and D. Herremans. 2018. Singing Voice Separation using a Deep Convolutional Neural Network Trained by Ideal Binary Mask and Cross Entropy. Neural Computing and Applications (2018) 1--14."},{"key":"e_1_3_2_1_24_1","volume-title":"Deep Clustering and Conventional Networks for Music Separation: Stronger Together. In ICASSP","author":"Luo Y.","year":"2017","unstructured":"Y. Luo , Z. Chen , J. R. Hershey , J. Le Roux , and N. Mesgarani . 2017 . Deep Clustering and Conventional Networks for Music Separation: Stronger Together. In ICASSP 2017 . 61--65. Y. Luo, Z. Chen, J. R. Hershey, J. Le Roux, and N. Mesgarani. 2017. Deep Clustering and Conventional Networks for Music Separation: Stronger Together. In ICASSP 2017. 61--65."},{"key":"e_1_3_2_1_25_1","volume-title":"MLSP","author":"Magoarou L. Le","year":"2013","unstructured":"L. Le Magoarou , A. Ozerov , and N. Duong . 2013. Text-Informed Audio Source Separation using Nonnegative Matrix Partial Co-Factorization . In MLSP 2013 . L. Le Magoarou, A. Ozerov, and N. Duong. 2013. Text-Informed Audio Source Separation using Nonnegative Matrix Partial Co-Factorization. In MLSP 2013."},{"key":"e_1_3_2_1_26_1","volume-title":"ACM IUI","author":"Nakano T.","year":"2016","unstructured":"T. Nakano , J. Kato , M. Hamasaki , and M. Goto . 2016. PlaylistPlayer: An Interface Using Multiple Criteria to Change the Playback Order of a Music Playlist . In ACM IUI 2016 . 186--190. T. Nakano, J. Kato, M. Hamasaki, and M. Goto. 2016. PlaylistPlayer: An Interface Using Multiple Criteria to Change the Playback Order of a Music Playlist. In ACM IUI 2016. 186--190."},{"key":"e_1_3_2_1_27_1","volume-title":"IEEE WASPAA","author":"Nakano T.","year":"2019","unstructured":"T. Nakano , K. Yoshii , Y. Wu , R. Nishikimi , K. W. E. Lin , and M. Goto . 2019. Joint Singing Pitch Estimation and Voice Separation Based on a Neural Harmonic Structure Renderer . In IEEE WASPAA 2019 . T. Nakano, K. Yoshii, Y. Wu, R. Nishikimi, K. W. E. Lin, and M. Goto. 2019. Joint Singing Pitch Estimation and Voice Separation Based on a Neural Harmonic Structure Renderer. In IEEE WASPAA 2019."},{"key":"e_1_3_2_1_28_1","volume-title":"Multichannel Nonnegative Tensor Factorization with Structured Constraints for User-guided Audio Source Separation. In ICASSP","author":"Ozerov A.","year":"2011","unstructured":"A. Ozerov , C. Fevotte , R. Blouet , and J.-L. Durrieu . 2011 . Multichannel Nonnegative Tensor Factorization with Structured Constraints for User-guided Audio Source Separation. In ICASSP 2011. A. Ozerov, C. Fevotte, R. Blouet, and J.-L. Durrieu. 2011. Multichannel Nonnegative Tensor Factorization with Structured Constraints for User-guided Audio Source Separation. In ICASSP 2011."},{"key":"e_1_3_2_1_29_1","volume-title":"ISMIR","author":"Raffel C.","year":"2014","unstructured":"C. Raffel , B. McFee , E. J. Humphrey , J. Salamon , O. Nieto , D. Liang , , and D. P. W. Ellis . 2014 . mir_eval: A Transparent Implementation of Common MIR Metrics . In ISMIR 2014. 367--372. C. Raffel, B. McFee, E. J. Humphrey, J. Salamon, O. Nieto, D. Liang, , and D. P. W. Ellis. 2014. mir_eval: A Transparent Implementation of Common MIR Metrics. In ISMIR 2014. 367--372."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2825440"},{"key":"e_1_3_2_1_31_1","volume-title":"WASPAA","author":"Smaragdis P.","year":"2009","unstructured":"P. Smaragdis and G. Mysore . 2009. \"Separation by Humming\": User Guided Sound Extraction from Monophonic Mixtures . In WASPAA 2009 . P. Smaragdis and G. Mysore. 2009. \"Separation by Humming\": User Guided Sound Extraction from Monophonic Mixtures. In WASPAA 2009."},{"key":"e_1_3_2_1_32_1","first-page":"330","article-title":"Wave-U-Net","volume":"2017","author":"Stoller D.","year":"2017","unstructured":"D. Stoller , S. Ewert , and S. Dixon . 2017 . Wave-U-Net : A Multi-scale Neural Network for End-to-end Audio Source Separation. In ISMIR 2017. 330 -- 340 . D. Stoller, S. Ewert, and S. Dixon. 2017. Wave-U-Net: A Multi-scale Neural Network for End-to-end Audio Source Separation. In ISMIR 2017. 330--340.","journal-title":"In ISMIR"},{"key":"e_1_3_2_1_33_1","first-page":"329","article-title":"Jointly Detecting and Separating Singing Voice","volume":"2018","author":"Stoller D.","year":"2018","unstructured":"D. Stoller , S. Ewert , and S. Dixon . 2018 . Jointly Detecting and Separating Singing Voice : A Multi-Task Approach. In LVA\/ICA 2018. 329 -- 339 . D. Stoller, S. Ewert, and S. Dixon. 2018. Jointly Detecting and Separating Singing Voice: A Multi-Task Approach. In LVA\/ICA 2018. 329--339.","journal-title":"A Multi-Task Approach. In LVA\/ICA"},{"key":"e_1_3_2_1_34_1","volume-title":"Multi-scale Multi-band DenseNets for Audio Source Separation. In WASPAA","author":"Takahashi N.","year":"2017","unstructured":"N. Takahashi and Y. Mitsufuji . 2017 . Multi-scale Multi-band DenseNets for Audio Source Separation. In WASPAA 2017 . 21--25. N. Takahashi and Y. Mitsufuji. 2017. Multi-scale Multi-band DenseNets for Audio Source Separation. In WASPAA 2017. 21--25."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2791721"},{"key":"e_1_3_2_1_36_1","volume-title":"Deep Interactive Object Selection. In CVPR","author":"Xu N.","year":"2016","unstructured":"N. Xu , B. L. Price , S. Cohen , J. Yang , and T. S. Huang . 2016 . Deep Interactive Object Selection. In CVPR 2016 . N. Xu, B. L. Price, S. Cohen, J. Yang, and T. S. Huang. 2016. Deep Interactive Object Selection. In CVPR 2016."}],"event":{"name":"IUI '20: 25th International Conference on Intelligent User Interfaces","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"],"location":"Cagliari Italy","acronym":"IUI '20"},"container-title":["Proceedings of the 25th International Conference on Intelligent User Interfaces"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3377325.3377539","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3377325.3377539","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:33:17Z","timestamp":1750199597000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3377325.3377539"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,17]]},"references-count":36,"alternative-id":["10.1145\/3377325.3377539","10.1145\/3377325"],"URL":"https:\/\/doi.org\/10.1145\/3377325.3377539","relation":{},"subject":[],"published":{"date-parts":[[2020,3,17]]},"assertion":[{"value":"2020-03-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}