{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T18:47:59Z","timestamp":1652726879610},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,6,26]],"date-time":"2013-06-26T00:00:00Z","timestamp":1372204800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1186\/1687-4722-2013-14","type":"journal-article","created":{"date-parts":[[2013,6,26]],"date-time":"2013-06-26T06:14:37Z","timestamp":1372227277000},"source":"Crossref","is-referenced-by-count":18,"title":["An iterative model-based approach to cochannel speech separation"],"prefix":"10.1186","volume":"2013","author":[{"given":"Ke","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,6,26]]},"reference":[{"key":"78_CR1","doi-asserted-by":"publisher","DOI":"10.1109\/9780470043387","volume-title":"Computational, Auditory Scene Analysis: Principles,Algorithms and Applications","author":"DL Wang","year":"2006","unstructured":"Wang DL, Brown GJ (eds): Computational, Auditory Scene Analysis: Principles,Algorithms and Applications. Hoboken: Wiley-IEEE Press; 2006."},{"key":"78_CR2","doi-asserted-by":"publisher","first-page":"2067","DOI":"10.1109\/TASL.2010.2041110","volume":"18","author":"G Hu","year":"2010","unstructured":"Hu G, Wang DL: A tandem algorithm for pitch estimation and voiced speech segregation. IEEE Trans. Audio, Speech, Lang. Process 2010, 18: 2067-2079.","journal-title":"IEEE Trans. Audio, Speech, Lang. Process"},{"key":"78_CR3","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1016\/j.specom.2009.02.003","volume":"51","author":"Y Shao","year":"2009","unstructured":"Shao Y, Wang DL: Sequential organization of speech in computational auditory scene analysis. Speech Comm 2009, 51: 657-667. 10.1016\/j.specom.2009.02.003","journal-title":"Speech Comm"},{"key":"78_CR4","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/j.csl.2008.03.004","volume":"24","author":"Y Shao","year":"2010","unstructured":"Shao Y, Srinivasan S, Jin Z, Wang DL: A computational auditory scene analysis system for speech segregation and robust speech recognition. Comput. Speech Lang 2010, 24: 77-93. 10.1016\/j.csl.2008.03.004","journal-title":"Comput. Speech Lang"},{"key":"78_CR5","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1109\/TASL.2006.881700","volume":"15","author":"G Hu","year":"2007","unstructured":"Hu G, Wang DL: Auditory segmentation based on onset and offset analysis. IEEE Trans. Audio, Speech, Lang. Process 2007, 15: 396-405.","journal-title":"IEEE Trans. Audio, Speech, Lang. Process"},{"key":"78_CR6","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.csl.2008.05.003","volume":"24","author":"J Barker","year":"2010","unstructured":"Barker J, Ma N, Coy A, Cooke M: Speech fragment decoding techniques for simultaneous speaker identification and speech recognition. Comput. Speech Lang 2010, 24: 94-111. 10.1016\/j.csl.2008.05.003","journal-title":"Comput. Speech Lang"},{"key":"78_CR7","first-page":"120","volume":"21","author":"K Hu","year":"2013","unstructured":"Hu K, Wang DL: An unsupervised approach to cochannel speech separation. IEEE Trans. Audio Speech Lang. Process 2013, 21: 120-129.","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"78_CR8","first-page":"793","volume":"13","author":"S Roweis","year":"2001","unstructured":"Roweis S, One microphone source separation: Adv. Neural Inf. Process. Syst. 2001, 13: 793-799.","journal-title":"Adv. Neural Inf. Process. Syst"},{"issue":"6","key":"78_CR9","doi-asserted-by":"publisher","first-page":"1766","DOI":"10.1109\/TASL.2007.901310","volume":"15","author":"A Reddy","year":"2007","unstructured":"Reddy A, Raj B: Soft mask methods for single-channel speaker separation. IEEE Trans. Audio, Speech, Lang. Process 2007, 15(6):1766-1776.","journal-title":"IEEE Trans. Audio, Speech, Lang. Process"},{"issue":"8","key":"78_CR10","doi-asserted-by":"publisher","first-page":"2299","DOI":"10.1109\/TASL.2007.904233","volume":"15","author":"MH Radfar","year":"2007","unstructured":"Radfar MH, Dansereau RM: Single-channel speech separation using soft masking filtering. IEEE Trans. Audio, Speech, Lang. Process 2007, 15(8):2299-2310.","journal-title":"IEEE Trans. Audio, Speech, Lang. Process"},{"key":"78_CR11","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.csl.2008.11.001","volume":"24","author":"JR Hershey","year":"2010","unstructured":"Hershey JR, Rennie SJ, Olsen PA, Kristjansson TT: Super-human multi-talker speech recognition: a graphical modeling approach. Comput. Speech Lang 2010, 24: 45-66. 10.1016\/j.csl.2008.11.001","journal-title":"Comput. Speech Lang"},{"key":"78_CR12","doi-asserted-by":"crossref","unstructured":"Stark M, Wohlmayr M, Pernkopf F: Source-filter-based single-channel speech separation using pitch information. IEEE Trans. Audio, Speech, Lang. Process 19(2):242-255.","DOI":"10.1109\/TASL.2010.2047419"},{"key":"78_CR13","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.csl.2008.03.003","volume":"24","author":"R Weiss","year":"2010","unstructured":"Weiss R, Ellis D: Speech separation using speaker-adapted eigenvoice speech models. Comput. Speech Lang 2010, 24: 16-29. 10.1016\/j.csl.2008.03.003","journal-title":"Comput. Speech Lang"},{"key":"78_CR14","volume-title":"Proc. 9th Int. Conf. Latent Variable Analysis and Signal Separation","author":"GJ Mysore","year":"2010","unstructured":"Mysore GJ, Smaragdis P, Raj B: Non-negative hidden Markov modeling of audio with application to source separation. In Proc. 9th Int. Conf. Latent Variable Analysis and Signal Separation. Heidelberg: Springer; 2010."},{"key":"78_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TASL.2006.876726","volume":"15","author":"P Smaragdis","year":"2007","unstructured":"Smaragdis P: Convolutive speech bases their application to supervised speech separation. IEEE Trans. Audio, Speech, Lang. Process 2007, 15: 1-12.","journal-title":"IEEE Trans. Audio, Speech, Lang. Process"},{"key":"78_CR16","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1109\/TASL.2010.2089520","volume":"19","author":"P Mowlaee","year":"2011","unstructured":"Mowlaee P, Christensen MG, Jensen SH: New results on single-channel speech separation using sinusoidal modeling. IEEE Trans. Audio Speech Lang. Process 2011, 19: 1265-1277.","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"78_CR17","first-page":"257","volume-title":"Proc. ICASSP-12 IEEE. Integrating multiple observations for model-based single-microphone speech separation with conditional random fields","author":"YT Yeung","year":"2012","unstructured":"Yeung YT, Lee T, Leung CC: Integrating multiple observations for model-based single-microphone speech separation with conditional random fields. In Proc. ICASSP-12 IEEE. New York; 2012:257-260."},{"key":"78_CR18","volume-title":"Proc. WASPAA IEEE","author":"MH Radfar","year":"2007","unstructured":"Radfar MH, Dansereau RM: Long-term gain estimation in model-based single channel speech separation. In Proc. WASPAA IEEE. New York; 2007."},{"key":"78_CR19","volume-title":"Scaled factorial hidden Markov models: a new technique for compensating gain differences in model-based single channel speech separation","author":"MH Radfar","year":"2010","unstructured":"Radfar MH, Wong W, Dansereau RM, Chan WY: Scaled factorial hidden Markov models: a new technique for compensating gain differences in model-based single channel speech separation. 2010."},{"issue":"9","key":"78_CR20","doi-asserted-by":"publisher","first-page":"2586","DOI":"10.1109\/TASL.2012.2208627","volume":"20","author":"P Mowlaee","year":"2012","unstructured":"Mowlaee P, Saeidi R, Christensen MG, Tan ZH, Kinnunen T, Franti P, Jensen SH: A joint approach for single-channel speaker identification and speech separation. Audio, Speech, and Language Processing, IEEE Transactions on 2012, 20(9):2586-2601.","journal-title":"Audio, Speech, and Language Processing, IEEE Transactions on"},{"key":"78_CR21","doi-asserted-by":"publisher","first-page":"4565","DOI":"10.1109\/ICPR.2010.1131","volume-title":"Pattern Recognition (ICPR), 2010 20th International Conference on IEEE,(IEEE","author":"R Saeidi","year":"2010","unstructured":"Saeidi R, Mowlaee P, Kinnunen T, Tan ZH, Christensen MG, Jensen SH, Franti P: Signal-to-signal ratio independent speaker identification for co-channel speech signals. In Pattern Recognition (ICPR), 2010 20th International Conference on IEEE,(IEEE. New York; 2010:4565-4568."},{"key":"78_CR22","doi-asserted-by":"publisher","first-page":"1495","DOI":"10.1109\/29.35387","volume":"37","author":"A N\u00e1das","year":"1989","unstructured":"N\u00e1das A, Nahamoo D, Picheny MA: Speech recognition using noise-adaptive prototypes. IEEE Trans. Acoust., Speech, Signal Process 1989, 37: 1495-1503. 10.1109\/29.35387","journal-title":"IEEE Trans. Acoust., Speech, Signal Process"},{"key":"78_CR23","first-page":"1","volume-title":"Proceedings of IWAENC 2012; International Workshop on VDE","author":"P Mowlaee","year":"2012","unstructured":"Mowlaee P, Martin R: On phase importance in parameter estimation for single-channel source separation, in Acoustic Signal Enhancement. In Proceedings of IWAENC 2012; International Workshop on VDE. New York: IEEE; 2012:1-4."},{"key":"78_CR24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115970","volume-title":"Hidden Markov model decomposition of speech and noise","author":"AP Varga","year":"1990","unstructured":"Varga AP, Moore RK: Hidden Markov model decomposition of speech and noise. 1990."},{"key":"78_CR25","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1109\/TSA.2005.854106","volume":"14","author":"Y Shao","year":"2006","unstructured":"Shao Y, Wang DL: Model-based sequential organization in cochannel speech. IEEE Trans. Audio, Speech, Lang. Process 2006, 14: 289-298.","journal-title":"IEEE Trans. Audio, Speech, Lang. Process"},{"key":"78_CR26","doi-asserted-by":"publisher","first-page":"2518","DOI":"10.1109\/TASL.2012.2205242","volume":"20","author":"A Narayanan","year":"2012","unstructured":"Narayanan A, Wang DL: A CASA based system for long-term, SNR estimation. IEEE Trans. Audio Speech Lang. Process 2012, 20: 2518-2527.","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"78_CR27","volume-title":"Speech, Separation Challenge","author":"M Cooke","year":"2006","unstructured":"Cooke M, Lee T: Speech, Separation Challenge. 21 September 2006.\n                    http:\/\/staffwww.dcs.shef.ac.uk\/people\/M.Cooke\/SpeechSeparation\n                    \n                   [ Challenge.htm]"},{"issue":"3","key":"78_CR28","first-page":"1486","volume":"126","author":"G Kim","year":"2009","unstructured":"Kim G, Lu Y, Hu Y, Loizou PC: An, algorithm that improves speech intelligibility in noise for normal-hearing listeners. 2009, 126(3):1486-1494.","journal-title":"An, algorithm that improves speech intelligibility in noise for normal-hearing listeners"},{"key":"78_CR29","doi-asserted-by":"publisher","first-page":"4214","DOI":"10.1109\/ICASSP.2010.5495701","volume-title":"A short-time objective intelligibility measure for time-frequency weighted noisy speech, in Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on IEEE","author":"CH Taal","year":"2010","unstructured":"Taal CH, Hendriks RC, Heusdens R, Jensen J: A short-time objective intelligibility measure for time-frequency weighted noisy speech, in Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on IEEE. 2010, 4214-4217."},{"issue":"6","key":"78_CR30","first-page":"66","volume":"27","author":"S Rennie","year":"2010","unstructured":"Rennie S, Hershey J, Olsen P: Single channel multi-talker speech recognition: graphical modeling approaches. IEEE Signal Process. Mag 2010, 27(6):66-80.","journal-title":"IEEE Signal Process. Mag"}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1687-4722-2013-14\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2013-14.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2013-14.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,21]],"date-time":"2019-01-21T20:59:13Z","timestamp":1548104353000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/1687-4722-2013-14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,6,26]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,12]]}},"alternative-id":["78"],"URL":"https:\/\/doi.org\/10.1186\/1687-4722-2013-14","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,6,26]]},"article-number":"14"}}