{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T15:05:40Z","timestamp":1770995140594,"version":"3.50.1"},"reference-count":42,"publisher":"Elsevier BV","issue":"2-3","license":[{"start":{"date-parts":[[2003,10,1]],"date-time":"2003-10-01T00:00:00Z","timestamp":1064966400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2003,10]]},"DOI":"10.1016\/s0167-6393(03)00010-4","type":"journal-article","created":{"date-parts":[[2003,5,1]],"date-time":"2003-05-01T00:39:38Z","timestamp":1051749578000},"page":"393-407","source":"Crossref","is-referenced-by-count":30,"title":["A spatio-temporal speech enhancement scheme for robust speech recognition in noisy environments"],"prefix":"10.1016","volume":"41","author":[{"given":"Erik","family":"Visser","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manabu","family":"Otsuka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Te-Won","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(03)00010-4_BIB1","doi-asserted-by":"crossref","unstructured":"Adami, A., Burget, L., Dupont, S., Garudadri, H., Grezl, F., Hermansky, H., Jain, P., Kajarekar, S., Morgan, N., Sivadas, S., 2002. QUALCOMM-ICSI-OGI features for ASR. In: Proc. ICSLP2002, pp. 21\u201324","DOI":"10.21437\/ICSLP.2002-4"},{"key":"10.1016\/S0167-6393(03)00010-4_BIB2","doi-asserted-by":"crossref","first-page":"1304","DOI":"10.1121\/1.1914702","article-title":"Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification","volume":"55","author":"Atal","year":"1974","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(03)00010-4_BIB3","article-title":"Speech denoising and dereverberation using probabilistic models","volume":"vol. 13","author":"Attias","year":"2001"},{"issue":"6","key":"10.1016\/S0167-6393(03)00010-4_BIB4","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1162\/neco.1995.7.6.1129","article-title":"An information-maximisation approach to blind separation and blind deconvolution","volume":"7","author":"Bell","year":"1995","journal-title":"Neural Comput."},{"key":"10.1016\/S0167-6393(03)00010-4_BIB5","doi-asserted-by":"crossref","unstructured":"Berouti, M., Schwartz, R., Makhoul, J., 1979. Enhancement of speech corrupted by acoustic noise. In: Proc. IEEE Conf. on Acoustics, Speech, and Signal Processing, pp. 208\u2013211","DOI":"10.1109\/ICASSP.1979.1170788"},{"key":"10.1016\/S0167-6393(03)00010-4_BIB6","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","article-title":"Suppression of acoustic noise in speech using spectral subtraction","volume":"ASSP-29","author":"Boll","year":"1979","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"2","key":"10.1016\/S0167-6393(03)00010-4_BIB7","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1006\/csla.1996.0024","article-title":"A practical methodology for speech source localization with microphone arrays","volume":"11","author":"Brandstein","year":"1997","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/S0167-6393(03)00010-4_BIB8","doi-asserted-by":"crossref","unstructured":"Buccigrossi, R.W., Simoncelli, E.P., 1997. Progressive wavelet image coding based on a conditional probability model. In: Proc. IEEE Internat. Conf. on Acoustics, Speech and Signal Processing, Munich","DOI":"10.1109\/ICASSP.1997.595412"},{"key":"10.1016\/S0167-6393(03)00010-4_BIB9","first-page":"362","article-title":"Blind beamforming for non gaussian signals","volume":"140","author":"Cardoso","year":"1993","journal-title":"IEEE Proc. F"},{"key":"10.1016\/S0167-6393(03)00010-4_BIB10","series-title":"Coherence and Time-Delay Estimation","year":"1993"},{"issue":"2","key":"10.1016\/S0167-6393(03)00010-4_BIB11","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1109\/89.486067","article-title":"Performance of time-delay estimation in the presence of room reverberation","volume":"4","author":"Champagne","year":"1996","journal-title":"IEEE Trans. Speech Audio Process"},{"key":"10.1016\/S0167-6393(03)00010-4_BIB12","article-title":"Delay estimation using narrow-band processes","author":"Chow","year":"1981","journal-title":"IEEE Trans. Acoust. Speech Signal Process"},{"issue":"5","key":"10.1016\/S0167-6393(03)00010-4_BIB13","doi-asserted-by":"crossref","first-page":"1518","DOI":"10.1109\/25.790527","article-title":"Acoustic noise and echo cancelling with microphone array","volume":"48","author":"Dahl","year":"1999","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"4","key":"10.1016\/S0167-6393(03)00010-4_BIB14","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1109\/29.1551","article-title":"Maximum a posteriori estimation of time-varying ARMA processes from noisy observations","volume":"36","author":"Dembo","year":"1988","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(03)00010-4_BIB15","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1111\/j.2517-6161.1995.tb02032.x","article-title":"Wavelet shrinkage: Asymptopia?","volume":"57","author":"Donoho","year":"1995","journal-title":"J. Roy. Statist. Soc. Ser. B"},{"key":"10.1016\/S0167-6393(03)00010-4_BIB16","doi-asserted-by":"crossref","unstructured":"Droppo, J., Deng, L., Acero, A., 2001. Evaluation of the SPLICE algorithm on the AURORA 2 database. In: Proc. Eurospeech 2001, Aalborg, Denmark, pp. 217\u2013220","DOI":"10.21437\/Eurospeech.2001-77"},{"key":"10.1016\/S0167-6393(03)00010-4_BIB17","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1109\/TASSP.1984.1164453","article-title":"Speech enhancement using a minimum-mean-square error short-time spectral amplitude estimator","volume":"ASSP-32","author":"Ephraim","year":"1984","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(03)00010-4_BIB18","doi-asserted-by":"crossref","DOI":"10.1109\/TASSP.1986.1164930","article-title":"Comparison of various time delay estimation methods by computer simulation","author":"Fertner","year":"1986","journal-title":"IEEE Trans. Acoust. Speech Signal Process"},{"issue":"3\u20134","key":"10.1016\/S0167-6393(03)00010-4_BIB19","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/S0167-6393(96)00054-4","article-title":"Beamforming microphone arrays for speech acquisition in noisy environments","volume":"20","author":"Fischer","year":"1996","journal-title":"Speech Comm."},{"issue":"November","key":"10.1016\/S0167-6393(03)00010-4_BIB20","article-title":"A parametric technique for time delay estimation","volume":"1","author":"Friedlander","year":"1984","journal-title":"IEEE Trans. Aerospace Electron. Syst."},{"issue":"4","key":"10.1016\/S0167-6393(03)00010-4_BIB21","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1109\/89.326616","article-title":"Rasta processing of speech","volume":"2","author":"Hermansky","year":"1994","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(03)00010-4_BIB22","unstructured":"Hirsch, H.G., Pearce, D., 2000. The AURORA experimental framework for the performance evaluations of speech recognition systems under noisy conditions, ISCA ITRW ASR2000 \u201cChallenges for the New Millennium\u201d, Paris, September"},{"key":"10.1016\/S0167-6393(03)00010-4_BIB23","series-title":"Wavelets, Time-Frequency Methods and Phase Space","article-title":"A real-time algorithm for signal analysis with the help of the wavelet transform","author":"Holschneider","year":"1989"},{"key":"10.1016\/S0167-6393(03)00010-4_BIB24","doi-asserted-by":"crossref","first-page":"1483","DOI":"10.1162\/neco.1997.9.7.1483","article-title":"A fast fixed-point algorithm for independent component analysis","volume":"9","author":"Hyvaerinen","year":"1997","journal-title":"Neural Comput."},{"key":"10.1016\/S0167-6393(03)00010-4_BIB25","series-title":"Array Signal Processing: Concepts and Techniques","author":"Johnson","year":"1993"},{"key":"10.1016\/S0167-6393(03)00010-4_BIB26","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/S0167-6393(97)00061-7","article-title":"Speech recognition in noisy environments using first-order vector Taylor series","volume":"24","author":"Kim","year":"1998","journal-title":"Speech Comm."},{"issue":"4","key":"10.1016\/S0167-6393(03)00010-4_BIB27","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1109\/TASSP.1976.1162830","article-title":"The generalized correlation method for estimation of time delay","volume":"24","author":"Knapp","year":"1976","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(03)00010-4_BIB28","unstructured":"Lee, T.-W., Bell, A., Lambert, R.H., 1997. Blind separation of delayed and convolved sources. In: Advances in Neural Information Processing Systems, vol. 9. Cambridge, MA, pp. 758\u2013764"},{"key":"10.1016\/S0167-6393(03)00010-4_BIB29","unstructured":"Lee, T.-W., Ziehe, A., Orglmeister, R., Sejnowski, T., 1998. Combining time-delayed decorrelation and ICA: towards solving the cocktail party problem. In: Proc. ICASSP, Seattle, WA, pp. 1249\u20131252"},{"issue":"1","key":"10.1016\/S0167-6393(03)00010-4_BIB30","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1109\/89.736335","article-title":"Evaluation of microphone arrays for enhancing noisy and reverberant speech for coding","volume":"7","author":"Li","year":"1999","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(03)00010-4_BIB31","doi-asserted-by":"crossref","unstructured":"Lieb, M., Fischer, A., 2001. Experiments with the Philips continuous ASR system on the AURORA noisy digits database. In: Proc. Eurospeech 2001, Aalborg, Denmark, pp. 625\u2013628","DOI":"10.21437\/Eurospeech.2001-165"},{"key":"10.1016\/S0167-6393(03)00010-4_BIB32","doi-asserted-by":"crossref","unstructured":"Macho, D., Mauuary, L., No, B., Cheng, Y.M., Ealey, D., Jouvet, D., Kelleher, H., Pearce, D., Saadoun, F., 2002. Evaluation of a noise-robust DSR front-end on AURORA databases. In: Proc. ICSLP 2002, pp. 17\u201320","DOI":"10.21437\/ICSLP.2002-3"},{"issue":"5","key":"10.1016\/S0167-6393(03)00010-4_BIB33","first-page":"365","article-title":"A microphone array for multimedia workstations","volume":"44","author":"Mahieux","year":"1996","journal-title":"J. Audio Eng. Soc."},{"key":"10.1016\/S0167-6393(03)00010-4_BIB34","article-title":"Independent component analysis of electroencephalographic data","volume":"vol. 8","author":"Makeig","year":"1995"},{"issue":"3","key":"10.1016\/S0167-6393(03)00010-4_BIB35","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1109\/89.668818","article-title":"Analysis of noise reduction and dereverberation techniques based on microphone arrays with postfiltering","volume":"6","author":"Marro","year":"1998","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"5","key":"10.1016\/S0167-6393(03)00010-4_BIB36","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1109\/89.466660","article-title":"Automatic word recognition in cars","volume":"3","author":"Mokbel","year":"1995","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(03)00010-4_BIB37","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1109\/89.841214","article-title":"Convolutive blind separation of non-stationary sources","volume":"8","author":"Parra","year":"2000","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(03)00010-4_BIB38","series-title":"Fundamentals of Speech Recognition","author":"Rabiner","year":"1993"},{"key":"10.1016\/S0167-6393(03)00010-4_BIB39","doi-asserted-by":"crossref","unstructured":"Silverman, H.F., Patterson, W.R., Flanagan, J.L., Rabinkin, D., 1997. A digital processing system for source location and sound capture by large microphone arrays. In: 1997 IEEE Internat. Conf. on Acoustics, Speech, and Signal Processing, Munich, Germany, vol. 1, pp. 251\u2013254","DOI":"10.1109\/ICASSP.1997.599616"},{"key":"10.1016\/S0167-6393(03)00010-4_BIB40","series-title":"Wavelets and Subband Coding","author":"Vetterli","year":"1995"},{"issue":"1","key":"10.1016\/S0167-6393(03)00010-4_BIB41","first-page":"17","article-title":"Broadband microphone arrays for speech acquisition","volume":"26","author":"Ward","year":"1998","journal-title":"Acoust. Aust."},{"key":"10.1016\/S0167-6393(03)00010-4_BIB42","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Cui, X., Iseli, M., Alwan, A., 2001. Noise robust feature extraction for ASR using the AURORA 2 database. In: Proc. Eurospeech 2001, Aalborg, Denmark, vol. 1, pp. 185\u2013188","DOI":"10.21437\/Eurospeech.2001-69"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639303000104?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639303000104?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T19:25:18Z","timestamp":1733945118000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639303000104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,10]]},"references-count":42,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[2003,10]]}},"alternative-id":["S0167639303000104"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(03)00010-4","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2003,10]]}}}