{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:27:08Z","timestamp":1740122828212,"version":"3.37.3"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T00:00:00Z","timestamp":1654819200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T00:00:00Z","timestamp":1654819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"national key r &d program of china","doi-asserted-by":"crossref","award":["2017YFB1002803"],"award-info":[{"award-number":["2017YFB1002803"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"national nature science foundation of china","doi-asserted-by":"crossref","award":["No. 61761044","U1903214"],"award-info":[{"award-number":["No. 61761044","U1903214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"national nature science foundation of china","doi-asserted-by":"crossref","award":["U1736206"],"award-info":[{"award-number":["U1736206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"basic research project of science and technology plan of shenzhen","award":["JCYJ20170818143246278"],"award-info":[{"award-number":["JCYJ20170818143246278"]}]},{"name":"hubei province technological in-novation major project","award":["2019AAA049"],"award-info":[{"award-number":["2019AAA049"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1007\/s11063-022-10887-6","type":"journal-article","created":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T19:02:39Z","timestamp":1654887759000},"page":"385-400","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Single-channel Multi-speakers Speech Separation Based on Isolated Speech Segments"],"prefix":"10.1007","volume":"55","author":[{"given":"Shanfa","family":"Ke","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9796-488X","authenticated-orcid":false,"given":"Zhongyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruimin","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaochen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,6,10]]},"reference":[{"issue":"4","key":"10887_CR1","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1109\/TASLP.2016.2528171","volume":"24","author":"Z-Q Wang","year":"2016","unstructured":"Wang Z-Q, Wang DL (2016) A joint training framework for robust automatic speech recognition. IEEE\/ACM Trans Audio Speech Lang Process 24(4):796\u2013806","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"4","key":"10887_CR2","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1109\/TASLP.2014.2304637","volume":"22","author":"J Li","year":"2014","unstructured":"Li J, Deng L, Gong Y, HaebUmbach R (2014) An overview of noise-robust automatic speech recognition. IEEE\/ACM Trans Audio Speech Lang Process 22(4):745\u2013777","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"4","key":"10887_CR3","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1109\/TASLP.2014.2305833","volume":"22","author":"A Narayanan","year":"2014","unstructured":"Narayanan A, Wang DL (2014) Investigation of speech separation as a front-end for noise robust speech recognition. IEEE\/ACM Trans Audio Speech Lang Process 22(4):826\u2013835","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"10887_CR4","volume-title":"Source separation for hearing aid applications","author":"MS Pedersen","year":"2006","unstructured":"Pedersen MS (2006) Source separation for hearing aid applications. IMM, Informatik og Matematisk Modelling, DTU, Lyngby"},{"issue":"4\u20135","key":"10887_CR5","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/S0893-6080(00)00026-5","volume":"13","author":"A Hyv\u00e4rinen","year":"2000","unstructured":"Hyv\u00e4rinen A, Oja E (2000) Independent component analysis: algorithms and applications. Neural Netw 13(4\u20135):411\u2013430","journal-title":"Neural Netw"},{"key":"10887_CR6","doi-asserted-by":"crossref","unstructured":"Aarabi P, Shi G, Jahromi O (2003) Robust speech separation using time-frequency masking. In: 2003 International conference on multimedia and expo. ICME\u201903. Proceedings (Cat. No. 03TH8698), vol\u00a01. IEEE, pp I\u2013741","DOI":"10.1109\/ICME.2003.1221024"},{"issue":"9","key":"10887_CR7","doi-asserted-by":"publisher","first-page":"1434","DOI":"10.1109\/TASLP.2014.2320637","volume":"22","author":"A Alinaghi","year":"2014","unstructured":"Alinaghi A, Jackson Philip JB, Liu Q, Wang W (2014) Joint mixing vector and binaural model based stereo source separation. IEEE\/ACM Trans Audio Speech Lang Process 22(9):1434\u20131448","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"2","key":"10887_CR8","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1109\/TASL.2012.2221459","volume":"21","author":"Y Wang","year":"2012","unstructured":"Wang Y, Han K, Wang DL (2012) Exploring monaural features for classification-based speech segregation. IEEE Trans Audio Speech Lang Process 21(2):270\u2013279","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"12","key":"10887_CR9","doi-asserted-by":"publisher","first-page":"1849","DOI":"10.1109\/TASLP.2014.2352935","volume":"22","author":"Y Wang","year":"2014","unstructured":"Wang Y, Narayanan A, Wang DL (2014) On training targets for supervised speech separation. IEEE\/ACM Trans Audio Speech Lang Process 22(12):1849\u20131858","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"3","key":"10887_CR10","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1109\/TASL.2006.885253","volume":"15","author":"T Virtanen","year":"2007","unstructured":"Virtanen T (2007) Monaural sound source separation by nonnegative matrix factorization with temporal continuity and sparseness criteria. IEEE Trans Audio Speech Lang Process 15(3):1066\u20131074","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"11","key":"10887_CR11","doi-asserted-by":"publisher","first-page":"2277","DOI":"10.1109\/TASL.2013.2263144","volume":"21","author":"T Virtanen","year":"2013","unstructured":"Virtanen T, Gemmeke JF, Raj B (2013) Active-set newton algorithm for overcomplete non-negative representations of audio. IEEE\/ACM Trans Audio Speech Lang Process 21(11):2277\u20132289","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"12","key":"10887_CR12","doi-asserted-by":"publisher","first-page":"2136","DOI":"10.1109\/TASLP.2015.2468583","volume":"23","author":"P-S Huang","year":"2015","unstructured":"Huang P-S, Kim M, Hasegawa-Johnson M, Smaragdis P (2015) Joint optimization of masks and deep recurrent neural networks for monaural source separation. IEEE\/ACM Trans Audio Speech Lang Process 23(12):2136\u20132147","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"10887_CR13","doi-asserted-by":"crossref","unstructured":"Yu D, Kolb\u00e6k M, Tan Z-H, Jensen J (2017) Permutation invariant training of deep models for speaker-independent multi-talker speech separation. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 241\u2013245","DOI":"10.1109\/ICASSP.2017.7952154"},{"issue":"10","key":"10887_CR14","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1109\/TASLP.2017.2726762","volume":"25","author":"M Kolb\u00e6k","year":"2017","unstructured":"Kolb\u00e6k M, Dong Yu, Tan Z-H, Jensen J (2017) Multitalker speech separation with utterance-level permutation invariant training of deep recurrent neural networks. IEEE\/ACM Trans Audio Speech Lang Process 25(10):1901\u20131913","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"10887_CR15","doi-asserted-by":"crossref","unstructured":"Hershey JR, Chen Z, Le\u00a0Roux J, Watanabe S (2016) Deep clustering: discriminative embeddings for segmentation and separation. In: 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 31\u201335","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"10887_CR16","doi-asserted-by":"crossref","unstructured":"Chen Z, Luo Y, Mesgarani N (2017) Deep attractor network for single-microphone speaker separation. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 246\u2013250","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"10887_CR17","doi-asserted-by":"crossref","unstructured":"Wang Z-Q, Le\u00a0Roux J, Hershey JR (2018) Alternative objective functions for deep clustering. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 686\u2013690","DOI":"10.1109\/ICASSP.2018.8462507"},{"key":"10887_CR18","doi-asserted-by":"crossref","unstructured":"Wang Z-Q, Le Roux J, Wang DL, Hershey JR (2018) End-to-end speech separation with unfolded iterative phase reconstruction. arXiv:1804.10204","DOI":"10.21437\/Interspeech.2018-1629"},{"key":"10887_CR19","doi-asserted-by":"crossref","unstructured":"Wang DL, Wang ZQ, Tan K (2019) Deep learning-based phase reconstruction for speaker separation: a trigonometric perspective, pp 71\u201375","DOI":"10.1109\/ICASSP.2019.8683231"},{"key":"10887_CR20","doi-asserted-by":"crossref","unstructured":"Luo Yi, Mesgarani Nima (2018) Tasnet: time-domain audio separation network for real-time, single-channel speech separation. In 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 696\u2013700","DOI":"10.1109\/ICASSP.2018.8462116"},{"issue":"8","key":"10887_CR21","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1109\/TASLP.2019.2915167","volume":"27","author":"Y Luo","year":"2019","unstructured":"Luo Y, Mesgarani N (2019) Conv-tasnet: surpassing ideal time-frequency magnitude masking for speech separation. IEEE\/ACM Trans Audio Speech Lang Process 27(8):1256\u20131266","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"10887_CR22","doi-asserted-by":"crossref","unstructured":"Tzinis E, Venkataramani S, Wang Z, Subakan C, Smaragdis P (2020) Two-step sound source separation: training on learned latent targets. In: ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 31\u201335","DOI":"10.1109\/ICASSP40776.2020.9054172"},{"key":"10887_CR23","doi-asserted-by":"crossref","unstructured":"Luo Y, Chen Z, Yoshioka T (2020) Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation. In: ICASSP 2020\u20142020 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 46\u201350","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"10887_CR24","doi-asserted-by":"crossref","unstructured":"Zeghidour N, Grangier D (2020) Wavesplit: end-to-end speech separation by speaker clustering. arXiv:2002.08933","DOI":"10.1109\/TASLP.2021.3099291"},{"issue":"2","key":"10887_CR25","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1250\/ast.41.465","volume":"41","author":"R Aihara","year":"2020","unstructured":"Aihara R, Wichern G, Le Roux J (2020) Deep clustering-based single-channel speech separation and recent advances. Acoust Sci Technol 41(2):465\u2013471","journal-title":"Acoust Sci Technol"},{"issue":"1","key":"10887_CR26","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/TASL.2012.2211015","volume":"21","author":"X Zheng","year":"2012","unstructured":"Zheng X, Ritz C, Xi J (2012) Encoding navigable speech sources: a psychoacoustic-based analysis-by-synthesis approach. IEEE Trans Audio Speech Lang Process 21(1):29\u201338","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"4","key":"10887_CR27","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"Vincent E, Gribonval R, F\u00e9votte C (2006) Performance measurement in blind audio source separation. IEEE Trans Audio Speech Lang Process 14(4):1462\u20131469","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"10887_CR28","unstructured":"Raffel C, McFee B, Humphrey EJ, Salamon J, Nieto O, Liang D, Ellis DPW, Raffel CC (2014) mir_eval: a transparent implementation of common mir metrics. In: Proceedings of the 15th international society for music information retrieval conference, ISMIR. Citeseer"},{"key":"10887_CR29","unstructured":"http:\/\/labrosa.ee.columbia.edu\/mireval\/"},{"key":"10887_CR30","doi-asserted-by":"crossref","unstructured":"Ke S, Hu R, Li G, Wu T, Wang X, Wang Z (2019) Multi-speakers speech separation based on modified attractor points estimation and GMM clustering. In: 2019 IEEE international conference on multimedia and expo (ICME). IEEE, pp 1414\u20131419","DOI":"10.1109\/ICME.2019.00245"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10887-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-022-10887-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10887-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T14:23:51Z","timestamp":1678112631000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-022-10887-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,10]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["10887"],"URL":"https:\/\/doi.org\/10.1007\/s11063-022-10887-6","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"type":"print","value":"1370-4621"},{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[2022,6,10]]},"assertion":[{"value":"9 May 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}