{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T20:42:58Z","timestamp":1725914578233},"publisher-location":"Cham","reference-count":62,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319646794"},{"type":"electronic","value":"9783319646800"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-64680-0_3","type":"book-chapter","created":{"date-parts":[[2017,10,31]],"date-time":"2017-10-31T08:37:26Z","timestamp":1509439046000},"page":"51-77","source":"Crossref","is-referenced-by-count":1,"title":["Multichannel Spatial Clustering Using Model-Based Source Separation"],"prefix":"10.1007","author":[{"given":"Michael I.","family":"Mandel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jon P.","family":"Barker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,7,26]]},"reference":[{"issue":"4","key":"3_CR1","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1109\/TSMCB.2002.804369","volume":"32","author":"P. Aarabi","year":"2002","unstructured":"Aarabi, P.: Self-localizing dynamic microphone arrays. IEEE Trans. Syst. Man Cybern. C 32(4), 474\u2013484 (2002)","journal-title":"IEEE Trans. Syst. Man Cybern. C"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Algazi, V.R., Duda, R.O., Thompson, D.M., Avendano, C.: The CIPIC HRTF database. In: Proceedings of WASPAA, pp. 99\u2013102 (2001)","DOI":"10.1109\/ASPAA.2001.969552"},{"issue":"7","key":"3_CR3","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1109\/TASL.2007.902460","volume":"15","author":"X. Anguera","year":"2007","unstructured":"Anguera, X., Wooters, C., Hernando, J.: Acoustic beamforming for speaker diarization of meetings. IEEE Trans. Audio Speech Language Process. 15(7), 2011\u20132022 (2007)","journal-title":"IEEE Trans. Audio Speech Language Process."},{"key":"3_CR4","doi-asserted-by":"crossref","first-page":"1833","DOI":"10.1016\/j.sigpro.2007.02.003","volume":"87","author":"S. Araki","year":"2007","unstructured":"Araki, S., Sawada, H., Mukai, R., Makino, S.: Underdetermined blind sparse source separation for arbitrarily arranged multiple sensors. Signal Process. 87, 1833\u20131847 (2007)","journal-title":"Signal Process."},{"key":"3_CR5","volume-title":"Combining spectral feature mapping and multi-channel model-based source separation for noise-robust automatic speech recognition","author":"D. Bagchi","year":"2015","unstructured":"Bagchi, D., Mandel, M.I., Wang, Z., He, Y., Plummer, A., Fosler-Lussier, E.: Combining spectral feature mapping and multi-channel model-based source separation for noise-robust automatic speech recognition. In: Proceedings of ASRU (2015)"},{"key":"3_CR6","volume-title":"The third \u201cCHiME\u201d speech separation and recognition challenge: dataset, task and baselines","author":"J. Barker","year":"2015","unstructured":"Barker, J., Marxer, R., Vincent, E., Watanabe, S.: The third \u201cCHiME\u201d speech separation and recognition challenge: dataset, task and baselines. In: Proceedings of ASRU (2015)"},{"issue":"3","key":"3_CR7","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1111\/j.2517-6161.1986.tb01412.x","volume":"48","author":"J. Besag","year":"1986","unstructured":"Besag, J.: On the statistical analysis of dirty pictures (with discussion). J. R. Stat. Soc. B 48(3), 259\u2013302 (1986)","journal-title":"J. R. Stat. Soc. B"},{"issue":"8","key":"3_CR8","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1109\/PROC.1969.7278","volume":"57","author":"J. Capon","year":"1969","unstructured":"Capon, J.: High-resolution frequency-wavenumber spectrum analysis. Proc. IEEE 57(8), 1408\u20131418 (1969)","journal-title":"Proc. IEEE"},{"issue":"2","key":"3_CR9","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/s10579-007-9040-x","volume":"41","author":"J. Carletta","year":"2007","unstructured":"Carletta, J.: Unleashing the killer corpus: experiences in creating the multi-everything AMI meeting corpus. Lang. Resour. Eval. 41(2), 181\u2013190 (2007)","journal-title":"Lang. Resour. Eval."},{"key":"3_CR10","volume-title":"Blind speech separation by combining beamformers and a time frequency binary mask","author":"J. Cermak","year":"2006","unstructured":"Cermak, J., Araki, S., Sawada, H., Makino, S.: Blind speech separation by combining beamformers and a time frequency binary mask. In: Proceedings of IWAENC, Paris (2006)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Cermak, J., Araki, S., Sawada, H., Makino, S.: Blind source separation based on a beamformer array and time frequency binary masking. In: Proceedings of ICASSP, vol. 1, pp. 145\u2013148. IEEE, New York (2007)","DOI":"10.1109\/ICASSP.2007.366637"},{"issue":"1","key":"3_CR12","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.compmedimag.2005.10.001","volume":"30","author":"K.S. Chuang","year":"2006","unstructured":"Chuang, K.S., Tzeng, H.L., Chen, S., Wu, J., Chen, T.J.: Fuzzy c-means clustering with spatial information for image segmentation. Comput. Med. Imaging Graph. 30(1), 9\u201315 (2006)","journal-title":"Comput. Med. Imaging Graph."},{"issue":"7","key":"3_CR13","doi-asserted-by":"crossref","first-page":"2059","DOI":"10.1109\/TASL.2012.2195654","volume":"20","author":"M. Cobos","year":"2012","unstructured":"Cobos, M., Lopez, J.: Maximum a posteriori binary mask estimation for underdetermined source separation using smoothed posteriors. IEEE Trans. Audio Speech Language Process. 20(7), 2059\u20132064 (2012)","journal-title":"IEEE Trans. Audio Speech Language Process."},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Deleforge, A., Forbes, F., Horaud, R.: Variational EM for binaural sound-source separation and localization. In: Proceedings of ICASSP, pp. 76\u201379 (2013)","DOI":"10.1109\/ICASSP.2013.6637612"},{"key":"3_CR15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A. Dempster","year":"1977","unstructured":"Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. B 39, 1\u201338 (1977)","journal-title":"J. R. Stat. Soc. B"},{"issue":"4","key":"3_CR16","doi-asserted-by":"crossref","first-page":"1383","DOI":"10.1109\/TSP.2008.2010596","volume":"57","author":"J. Dmochowski","year":"2009","unstructured":"Dmochowski, J., Benesty, J., Affes, S.: On spatial aliasing in microphone arrays. IEEE Trans. Signal Process. 57(4), 1383\u20131395 (2009)","journal-title":"IEEE Trans. Signal Process."},{"issue":"3","key":"3_CR17","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1109\/89.759034","volume":"7","author":"M. Gales","year":"1999","unstructured":"Gales, M.: Semi-tied covariance matrices for hidden Markov models. IEEE Trans. Audio Speech Language Process. 7(3), 272\u2013281 (1999)","journal-title":"IEEE Trans. Audio Speech Language Process."},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Gaubitch, N.D., Kleijn, W.B., Heusdens, R.: Auto-localization in ad-hoc microphone arrays. In: Proceedings of ICASSP, pp. 106\u2013110. IEEE, New York (2013)","DOI":"10.1109\/ICASSP.2013.6637618"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Grais, E., Erdogan, H.: Spectro-temporal post-smoothing in NMF based single-channel source separation. In: Proceedings of EUSIPCO, pp. 584\u2013588 (2012)","DOI":"10.21437\/Interspeech.2013-726"},{"issue":"2","key":"3_CR20","first-page":"184","volume":"152","author":"D.B. Gu","year":"2004","unstructured":"Gu, D.B., Sun, J.: EM image segmentation algorithm based on an inhomogeneous hidden MRF model. IEEE Vis. Image Signal Process. 152(2), 184\u2013190 (2004)","journal-title":"IEEE Vis. Image Signal Process."},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Haeb-Umbach, R., Ney, H.: Linear discriminant analysis for improved large vocabulary continuous speech recognition. In: Proceedings of ICASSP, pp. 13\u201316 (1992)","DOI":"10.1109\/ICASSP.1992.225984"},{"issue":"4","key":"3_CR22","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1109\/TASL.2010.2055560","volume":"19","author":"I. Himawan","year":"2011","unstructured":"Himawan, I., McCowan, I., Sridharan, S.: Clustered blind beamforming from ad-hoc microphone arrays. IEEE Trans. Audio Speech Language Process. 19(4), 661\u2013676 (2011)","journal-title":"IEEE Trans. Audio Speech Language Process."},{"issue":"6","key":"3_CR23","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G. Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., Yu, D., Dahl, G.E., Mohamed, A., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T.N., Kingsbury, B.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82\u201397 (2012)","journal-title":"IEEE Signal Process. Mag."},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Wang, D., Liu, R.: Binaural deep neural network classification for reverberant speech segregation. In: Proceedings of Interspeech, pp. 2400\u20132403 (2014)","DOI":"10.1109\/TASLP.2014.2361023"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Kim, M., Smaragdis, P.: Single channel source separation using smooth nonnegative matrix factorization with Markov random fields. In: Proceedings of MLSP, pp. 1\u20136 (2013)","DOI":"10.1109\/MLSP.2013.6661909"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Kim, M., Smaragdis, P., Ko, G.G., Rutenbar, R.A.: Stereophonic spectrogram segmentation using Markov random fields. In: Proceedings of MLSP, pp. 1\u20136 (2012)","DOI":"10.1109\/MLSP.2012.6349754"},{"key":"3_CR27","volume-title":"The REVERB challenge: a common evaluation framework for dereverberation and recognition of reverberant speech","author":"K. Kinoshita","year":"2013","unstructured":"Kinoshita, K., Delcroix, M., Yoshioka, T., Nakatani, T., Habets, E., Sehr, A., Kellermann, W., Gannot, S., Maas, R., Haeb-Umbach, R., Leutnant, V., Raj, B.: The REVERB challenge: a common evaluation framework for dereverberation and recognition of reverberant speech. In: Proceedings of WASPAA, New Paltz, NY (2013)"},{"key":"3_CR28","volume-title":"Smooth soft mel-spectrographic masks based on blind sparse source separation","author":"M. K\u00fchne","year":"2007","unstructured":"K\u00fchne, M., Togneri, R., Nordholm, S.: Smooth soft mel-spectrographic masks based on blind sparse source separation. In: Proceedings of Interspeech (2007)"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"K\u00fchne, M., Togneri, R., Nordholm, S.: Adaptive beamforming and soft missing data decoding for robust speech recognition in reverberant environments. In: Proceedings of Interspeech, pp. 976\u2013979 (2008)","DOI":"10.21437\/Interspeech.2008-285"},{"issue":"2","key":"3_CR30","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1016\/j.sigpro.2009.08.005","volume":"90","author":"M. K\u00fchne","year":"2010","unstructured":"K\u00fchne, M., Togneri, R., Nordholm, S.: A novel fuzzy clustering algorithm using observation weighting and context information for reverberant blind speech separation. Signal Process. 90(2), 653\u2013669 (2010)","journal-title":"Signal Process."},{"issue":"10","key":"3_CR31","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1109\/LSP.2012.2209643","volume":"19","author":"S. Liang","year":"2012","unstructured":"Liang, S., Liu, W., Jiang, W.: Integrating binary mask estimation with MRF priors of cochleagram for speech separation. IEEE Signal Process. Lett. 19(10), 627\u2013630 (2012)","journal-title":"IEEE Signal Process. Lett."},{"key":"3_CR32","first-page":"705","volume":"12","author":"R. Lippmann","year":"1987","unstructured":"Lippmann, R., Martin, E., Paul, D.: Multi-style training for robust isolated-word speech recognition. In: Proceedings of ICASSP, vol. 12, pp. 705\u2013708 (1987)","journal-title":"In: Proceedings of ICASSP"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, Z., He, L.W., Chou, P.: Energy-based sound source localization and gain normalization for ad hoc microphone arrays. In: Proceedings of ICASSP, vol. 2, pp. 761\u2013764. IEEE, New York (2007)","DOI":"10.1109\/ICASSP.2007.366347"},{"issue":"2","key":"3_CR34","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"S.P. Lloyd","year":"1982","unstructured":"Lloyd, S.P.: Least squares quantization in PCM. IEEE Trans. Inf. Theory 28(2), 129\u2013137 (1982)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Madhu, N., Breithaupt, C., Martin, R.: Temporal smoothing of spectral masks in the cepstral domain for speech separation. In: Proceedings of ICASSP, pp. 45\u201348 (2008)","DOI":"10.1109\/ICASSP.2008.4517542"},{"key":"3_CR36","volume-title":"Enforcing consistency in spectral masks using Markov random fields","author":"M.I. Mandel","year":"2015","unstructured":"Mandel, M.I., Roman, N.: Enforcing consistency in spectral masks using Markov random fields. In: Proceedings of EUSIPCO (2015)"},{"issue":"2","key":"3_CR37","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1109\/TASL.2009.2029711","volume":"18","author":"M.I. Mandel","year":"2010","unstructured":"Mandel, M.I., Weiss, R.J., Ellis, D.P.W.: Model-based expectation maximization source separation and localization. IEEE Trans. Audio Speech Language Process. 18(2), 382\u2013394 (2010)","journal-title":"IEEE Trans. Audio Speech Language Process."},{"key":"3_CR38","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1146\/annurev.ps.42.020191.001031","volume":"42","author":"J.C. Middlebrooks","year":"1991","unstructured":"Middlebrooks, J.C., Green, D.M.: Sound localization by human listeners. Annu. Rev. Psychol. 42, 135\u2013159 (1991)","journal-title":"Annu. Rev. Psychol."},{"issue":"4","key":"3_CR39","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1109\/TASLP.2014.2305833","volume":"22","author":"A. Narayanan","year":"2014","unstructured":"Narayanan, A., Wang, D.: Investigation of speech separation as a front-end for noise robust speech recognition. IEEE Trans. Audio Speech Language Process. 22(4), 826\u2013835 (2014)","journal-title":"IEEE Trans. Audio Speech Language Process."},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"O\u2019Grady, P.D., Pearlmutter, B.A.: Soft-LOST: EM on a mixture of oriented lines. In: Independent Component Analysis and Blind Signal Separation, vol. 3195, 1270 pp. Springer, Berlin (2004)","DOI":"10.1007\/978-3-540-30110-3_55"},{"key":"3_CR41","volume-title":"Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference","author":"J. Pearl","year":"1988","unstructured":"Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco, CA (1988)"},{"key":"3_CR42","doi-asserted-by":"crossref","unstructured":"Povey, D., Kanevsky, D., Kingsbury, B., Ramabhadran, B., Saon, G., Visweswariah, K.: Boosted MMI for model and feature-space discriminative training. In: Proceedings of ICASSP, pp. 4057\u20134060 (2008)","DOI":"10.1109\/ICASSP.2008.4518545"},{"issue":"3","key":"3_CR43","doi-asserted-by":"crossref","first-page":"1003","DOI":"10.1109\/TSP.2006.888896","volume":"55","author":"B. Rafaely","year":"2007","unstructured":"Rafaely, B., Weiss, B., Bachmat, E.: Spatial aliasing in spherical microphone arrays. IEEE Trans. Signal Process. 55(3), 1003\u20131010 (2007)","journal-title":"IEEE Trans. Signal Process."},{"key":"3_CR44","volume-title":"Recognition and understanding of meetings: the AMI and AMIDA projects","author":"S. Renals","year":"2007","unstructured":"Renals, S., Hain, T., Bourlard, H.: Recognition and understanding of meetings: the AMI and AMIDA projects. In: Proceedings of ASRU, Kyoto (2007)"},{"key":"3_CR45","doi-asserted-by":"crossref","first-page":"2236","DOI":"10.1121\/1.1610463","volume":"114","author":"N. Roman","year":"2003","unstructured":"Roman, N., Wang, D.L., Brown, G.J.: Speech segregation based on sound localization. J. Acoust. Soc. Am. 114, 2236\u20132252 (2003)","journal-title":"J. Acoust. Soc. Am."},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Roweis, S.: Factorial models and refiltering for speech separation and denoising. In: Proceedings of Eurospeech, Geneva, pp. 1009\u20131012 (2003)","DOI":"10.21437\/Eurospeech.2003-345"},{"key":"3_CR47","volume-title":"Learning the speech front-end with raw waveform CLDNNS","author":"T.N. Sainath","year":"2015","unstructured":"Sainath, T.N., Weiss, R.J., Senior, A., Wilson, K.W., Vinyals, O.: Learning the speech front-end with raw waveform CLDNNS. In: Proceedings of Interspeech (2015)"},{"issue":"5","key":"3_CR48","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1109\/TSA.2004.832994","volume":"12","author":"H. Sawada","year":"2004","unstructured":"Sawada, H., Mukai, R., Araki, S., Makino, S.: A robust and precise method for solving the permutation problem of frequency-domain blind source separation. IEEE Trans. Speech Audio Process. 12(5), 530\u2013538 (2004)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"3","key":"3_CR49","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1109\/TASL.2010.2051355","volume":"19","author":"H. Sawada","year":"2011","unstructured":"Sawada, H., Araki, S., Makino, S.: Underdetermined convolutive blind source separation via frequency bin-wise clustering and permutation alignment. IEEE Trans. Audio Speech Language Process. 19(3), 516\u2013527 (2011)","journal-title":"IEEE Trans. Audio Speech Language Process."},{"issue":"2","key":"3_CR50","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1109\/TASL.2009.2025790","volume":"18","author":"M. Souden","year":"2010","unstructured":"Souden, M., Benesty, J., Affes, S.: On optimal frequency-domain multichannel linear filtering for noise reduction. IEEE Trans. Audio Speech Language Process. 18(2), 260\u2013276 (2010)","journal-title":"IEEE Trans. Audio Speech Language Process."},{"key":"3_CR51","volume-title":"Hybrid acoustic models for distant and multichannel large vocabulary speech recognition","author":"P. Swietojanski","year":"2013","unstructured":"Swietojanski, P., Ghoshal, A., Renals, S.: Hybrid acoustic models for distant and multichannel large vocabulary speech recognition. In: Proceedings of ASRU (2013)"},{"issue":"6","key":"3_CR52","doi-asserted-by":"crossref","first-page":"1068","DOI":"10.1109\/TPAMI.2007.70844","volume":"30","author":"R. Szeliski","year":"2008","unstructured":"Szeliski, R., Zabih, R., Scharstein, D., Veksler, O., Kolmogorov, V., Agarwala, A., Tappen, M., Rother, C.: A comparative study of energy minimization methods for Markov random fields with smoothness-based priors. IEEE Trans. Pattern Anal. Mach. Intell. 30(6), 1068\u20131080 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR53","volume-title":"Stepwise phase difference restoration method for sound source localization using multiple microphone pairs","author":"M. Togami","year":"2007","unstructured":"Togami, M., Sumiyoshi, T., Amano, A.: Stepwise phase difference restoration method for sound source localization using multiple microphone pairs. In: Proceedings of ICASSP (2007)"},{"key":"3_CR54","doi-asserted-by":"crossref","unstructured":"Traa, J., Kim, M., Smaragdis, P.: Phase and level difference fusion for robust multichannel source separation. In: Proceedings of ICASSP, pp. 6687\u20136690 (2014)","DOI":"10.1109\/ICASSP.2014.6854894"},{"key":"3_CR55","doi-asserted-by":"crossref","unstructured":"Vesel\u00fd, K., Ghoshal, A., Burget, L., Povey, D.: Sequence-discriminative training of deep neural networks. In: Proceedings of Interspeech, pp. 2345\u20132349 (2013)","DOI":"10.21437\/Interspeech.2013-548"},{"key":"3_CR56","doi-asserted-by":"crossref","unstructured":"Vincent, E.: An experimental evaluation of Wiener filter smoothing techniques applied to under-determined audio source separation. In: International Conference on Latent Variable Analysis and Signal Separation, pp. 157\u2013164. Springer, Berlin, Heidelberg (2010)","DOI":"10.1007\/978-3-642-15995-4_20"},{"issue":"3","key":"3_CR57","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1109\/MSP.2013.2297440","volume":"31","author":"E. Vincent","year":"2014","unstructured":"Vincent, E., Bertin, N., Gribonval, R., Bimbot, F.: From blind to guided audio source separation: how models and side information can improve the separation of sound. IEEE Signal Process. Mag. 31(3), 107\u2013115 (2014)","journal-title":"IEEE Signal Process. Mag."},{"key":"3_CR58","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/0-387-22794-6_12","volume-title":"Speech Separation by Humans and Machines","author":"D. Wang","year":"2005","unstructured":"Wang, D.: On ideal binary mask as the computational goal of auditory scene analysis. In: Divenyi, P. (ed.) Speech Separation by Humans and Machines, pp. 181\u2013197. Springer US, Boston, MA (2005)"},{"issue":"5","key":"3_CR59","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1016\/j.specom.2011.01.003","volume":"53","author":"R. Weiss","year":"2011","unstructured":"Weiss, R., Mandel, M.I., Ellis, D.W.P.: Combining localization cues and source model constraints for binaural source separation. Speech Commun. 53(5), 606\u2013621 (2011)","journal-title":"Speech Commun."},{"key":"3_CR60","unstructured":"Yedidia, J., Freeman, W., Weiss, Y.: Generalized belief propagation. In: Advances in Neural Information Processing Systems, pp. 689\u2013695. MIT, Cambridge (2000)"},{"issue":"7","key":"3_CR61","first-page":"1830","volume":"52","author":"O. Yilmaz","year":"2004","unstructured":"Yilmaz, O., Rickard, S.: Blind separation of speech mixtures via time\u2013frequency masking. IEEE Trans. Audio Speech Language Process. 52(7), 1830\u20131847 (2004)","journal-title":"IEEE Trans. Audio Speech Language Process."},{"issue":"1","key":"3_CR62","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/42.906424","volume":"20","author":"Y. Zhang","year":"2001","unstructured":"Zhang, Y., Brady, M., Smith, S.: Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm. IEEE Trans. Med. Imaging 20(1), 45\u201357 (2001)","journal-title":"IEEE Trans. Med. Imaging"}],"container-title":["New Era for Robust Speech Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-64680-0_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T05:02:17Z","timestamp":1719550937000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-64680-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319646794","9783319646800"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-64680-0_3","relation":{},"subject":[],"published":{"date-parts":[[2017]]}}}