{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:40:34Z","timestamp":1742913634186,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":51,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642213168"},{"type":"electronic","value":"9783642213175"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-21317-5_12","type":"book-chapter","created":{"date-parts":[[2011,7,12]],"date-time":"2011-07-12T13:32:24Z","timestamp":1310477544000},"page":"319-344","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Recognition of Multiple Speech Sources Using ICA"],"prefix":"10.1007","author":[{"given":"Eugen","family":"Hoffmann","sequence":"first","affiliation":[]},{"given":"Dorothea","family":"Kolossa","sequence":"additional","affiliation":[]},{"given":"Reinhold","family":"Orglmeister","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2011,6,23]]},"reference":[{"key":"12_CR1","doi-asserted-by":"publisher","DOI":"10.1002\/0471221317","volume-title":"Independent Component Analysis","author":"A Hyv\u00e4rinen","year":"2001","unstructured":"A. Hyv\u00e4rinen, J. Karhunen, E. Oja, Independent Component Analysis, New York: John Wiley, 2001."},{"key":"12_CR2","unstructured":"A. Mansour and M. Kawamoto, \u201cICA papers classified according to their applications and performances,\u201d in IEICA Trans. Fundamentals, vol.\u00a0E86-A, no.\u00a03, pp. 620\u2013633, March 2003."},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"M. S. Pedersen, J. Larsen, U. Kjems and L. C. Parra, \u201cConvolutive blind source separation methods\u201d, in Springer Handbook of Speech Processing and Speech Communication, pp. 1065\u20131094, Springer Verlag Berlin Heidelberg, 2008.","DOI":"10.1007\/978-3-540-49127-9_52"},{"key":"12_CR4","unstructured":"J. Anem\u00fcller and B. Kollmeier, \u201cAmplitude modulation decorrelation for convolutive blind source separation\u201d, in Proc. ICA 2000, Helsinki, pp. 215\u2013220, 2000."},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"L. Deng, J. Droppo and A. Acero, \u201cDynamic compensation of HMM variances using the feature enhancement uncertainty computed from a parametric model of speech distortion\u201d, in IEEE Trans. Speech and Audio Processing, vol.\u00a013, no.\u00a03, pp.\u00a0412\u2013421, May 2005.","DOI":"10.1109\/TSA.2005.845814"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"D. Kolossa, R. F. Astudillo, E. Hoffmann and R. Orglmeister, \u201cIndependent Component Analysis and Time-Frequency Masking for Speech Recognition in Multitalker Conditions\u201d, in EURASIP J. on Audio, Speech, and Music Processing, vol. 2010, article ID 651420, 2010.","DOI":"10.1186\/1687-4722-2010-651420"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"D. Kolossa, A. Klimas and R. Orglmeister, \u201cSeparation and robust recognition of noisy, convolutive speech mixtures using time-frequency masking and missing data techniques\u201d, in Proc. Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), pp. 82\u201385, Oct. 2005.","DOI":"10.1109\/ASPAA.2005.1540174"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"K.\u00a0Kumatani, J.\u00a0McDonough, D.\u00a0Klakow, P.\u00a0Garner, and W.\u00a0Li, \u201cAdaptive beamforming with a maximum negentropy criterion,\u201d in Proc. HSCMA, 2008.","DOI":"10.1109\/HSCMA.2008.4538716"},{"issue":"7","key":"12_CR9","doi-asserted-by":"publisher","first-page":"1830","DOI":"10.1109\/TSP.2004.828896","volume":"52","author":"O Yilmaz","year":"2004","unstructured":"O.\u00a0Yilmaz and S.\u00a0Rickard, \u201cBlind separation of speech mixtures via time-frequency masking,\u201d IEEE Trans. Signal Processing, vol.\u00a052, no.\u00a07, pp. 1830\u20131847, July 2004.","journal-title":"IEEE Trans. Signal Processing"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"M.\u00a0K\u00fchne, R.\u00a0Togneri, and S.\u00a0Nordholm, \u201cTime-frequency masking: Linking blind source separation and robust speech recognition,\u201d in Speech Recognition, Technologies and Applications. I-Tech, 2008.","DOI":"10.5772\/6382"},{"key":"12_CR11","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1006\/csla.1994.1016","volume":"8","author":"G Brown","year":"1994","unstructured":"G.\u00a0Brown and M.\u00a0Cooke, \u201cComputational auditory scene analysis,\u201d Computer Speech and Language, vol.\u00a08, pp. 297\u2013336, 1994.","journal-title":"Computer Speech and Language"},{"key":"12_CR12","doi-asserted-by":"publisher","first-page":"1558","DOI":"10.1109\/PROC.1977.10770","volume":"65","author":"JB Allen","year":"1977","unstructured":"J. B. Allen and L. R. Rabiner, \u201cA unified approach to short-time Fourier analysis and synthesis,\u201d Proc. IEEE, vol. 65, pp. 1558\u20131564, Nov. 1977.","journal-title":"Proc. IEEE"},{"issue":"6","key":"12_CR13","first-page":"362","volume":"140","author":"J-F Cardoso","year":"1993","unstructured":"J.-F. Cardoso and A. Souloumiac, \u201cBlind beamforming for non-Gaussian signals,\u201d Radar and Signal Processing, IEEE Proceedings, F 140(6), pp. 362-370, Dec. 1993.","journal-title":"F"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"A. Belouchrani, K. Abed Meraim, J.-F. Cardoso and E. Moulines, \u201cA blind source separation technique based on second order statistics,\u201d in EEE Trans. on Signal Processing, vol. 45(2), pp. 434-444, 1997.","DOI":"10.1109\/78.554307"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"A. Bell and T. Sejnowski, \u201cAn information-maximization approach to blind separation and blind deconvolution,\u201d in Neural Computation, vol. 7, pp. 1129\u20131159, 1995.","DOI":"10.1162\/neco.1995.7.6.1129"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"L. Deng and J. Droppo and A. Acero, \u201cDynamic compensation of HMM variances using the feature enhancement uncertainty computed from a parametric model of speech distortion,\u201d in IEEE Trans. Speech and Audio Processing, vol. 13, pp. 412\u2013421, 2005.","DOI":"10.1109\/TSA.2005.845814"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"A. Hyv\u00e4rinen and E. Oja. A fast fixed-point algorithm for independent component analysis. in Neural Computation, vol. 9, pp. 1483\u20131492, 1997.","DOI":"10.1162\/neco.1997.9.7.1483"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"T. Kristjansson and B. Frey. Accounting for uncertainty in observations: A new paradigm for robust automatic speech recognition, in Proc. ICASSP, 2002.","DOI":"10.1109\/ICASSP.2002.5743654"},{"key":"12_CR19","unstructured":"C. Mejuto, A. Dapena and L. Castedo, \u201cFrequency-domain infomax for blind separation of convolutive mixtures\u201d, in Proc. ICA 2000, pp. 315\u2013320, Helsinki, 2000."},{"issue":"1\u20134","key":"12_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0925-2312(00)00345-3","volume":"41","author":"N Murata","year":"2001","unstructured":"N. Murata, S. Ikeda, and A. Ziehe, \u201cAn approach to blind source separation based on temporal structure of speech signals,\u201d Neurocomputing, vol. 41, no. 1\u20134, pp. 1\u201324, Oct. 2001.","journal-title":"Neurocomputing"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"L. Parra, C. Spence and B. De Vries, \u201cConvolutive blind source separation based on multiple decorrelation.\u201d in Proc. IEEE NNSP workshop, pp. 23\u201332, Cambridge, UK, 1998.","DOI":"10.1109\/NNSP.1998.710626"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"K. Kamata, X. Hu, and H. Kobatake, \u201cA new approach to the permutation problem in frequency domain blind source separation,\u201d in Proc. ICA 2004, pp. 849\u2013856, Granada, Spain, September 2004.","DOI":"10.1007\/978-3-540-30110-3_107"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"D.-T. Pham, C. Servi\u00e8re, and H. Boumaraf, \u201cBlind separation of speech mixtures based on nonstationarity\u201d in IEEE Signal Processing and Its Applications, Proceedings of the Seventh International Symposium, pp. 73\u201376, 2003.","DOI":"10.1109\/ISSPA.2003.1224818"},{"key":"12_CR24","unstructured":"W. Baumann, D. Kolossa and R. Orglmeister, \u201cMaximum likelihood permutation correction for convolutive source separation,\u201d in ICA 2003, pp. 373\u2013378, 2003."},{"key":"12_CR25","unstructured":"S. Kurita, H. Saruwatari, S. Kajita, K. Takeda, and F. Itakura, \u201cEvaluation of frequency-domain blind signal separation using directivity pattern under reverberant conditions,\u201d in ICASSP2000, pp. 3140\u20133143, 2000."},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"M. Ikram and D. Morgan, \u201cA beamforming approach to permutation alignment for multichannel frequency-domain blind speech separation,\u201d in ICASSP02, pp. 881\u2013884, 2002.","DOI":"10.1109\/ICASSP.2002.1005881"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"N. Mitianoudis and M. Davies, \u201cPermutation alignment for frequency domain ICA using subspace beamforming methods\u201d, in Proc. ICA 2004, LNCS 3195, pp. 669\u2013676, 2004.","DOI":"10.1007\/978-3-540-30110-3_85"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"H. Sawada, R. Mukai, S. Araki, S. Makino, \u201cA robust approach to the permutation problem of frequency-domain blind source separation,\u201d in Proc. ICASSP, vol. V, pp. 381\u2013384, Apr. 2003.","DOI":"10.1109\/ICASSP.2003.1199969"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"V. Stouten and H. Van hamme and P. Wambacq, \u201cApplication of minimum statistics and minima controlled recursive averaging methods to estimate a cepstral noise model for robust ASR,\u201d in Proc. ICASSP, vol. 1, May 2006.","DOI":"10.1109\/ICASSP.2006.1660133"},{"key":"12_CR30","unstructured":"D.-T. Pham, C. Servi\u00e8re, and H. Boumaraf, \u201cBlind separation of convolutive audio mixtures using nonstationarity,\u201d in Proc. ICA2003, pp. 981\u2013986, 2003."},{"key":"12_CR31","volume-title":"\u201cA sparsity-based method to solve permutation indeterminacy in frequency-domain convolutive blind source separation\u201d, in Independent Component Analysis and Signal Separation: 8th International Conference, ICA 2009, Proceedings","author":"P Sudhakar","year":"2009","unstructured":"P. Sudhakar, and R. Gribonval, \u201cA sparsity-based method to solve permutation indeterminacy in frequency-domain convolutive blind source separation,\u201d in Independent Component Analysis and Signal Separation: 8th International Conference, ICA 2009, Proceedings, Paraty, Brazil, March 2009."},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"M. Van Segbroeck and H. Van hamme, \u201cRobust speech recognition using missing data techniques in the prospect domain and fuzzy masks,\u201d in Proc. ICASSP, pp. 4393\u20134396, 2008.","DOI":"10.1109\/ICASSP.2008.4518629"},{"key":"12_CR33","unstructured":"W. Baumann, and B.-U. Khler, and D. Kolossa, and R. Orglmeister, \u201cReal time separation of convolutive mixtures.\u201d in: Independent Component Analysis and Blind Signal Separation: 4th International Symposium, ICA 2001, Proceedings, San Diego, USA, 2001."},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"F. Asano, S. Ikeda, M. Ogawa, H. Asoh, and N. Kitawaki, \u201cCombined approach of array processing and independent component analysis for blind separation of acoustic signals,\u201d in IEEE Trans. Speech Audio Proc., vol. 11, no. 3, pp. 204\u2013215, May 2003.","DOI":"10.1109\/TSA.2003.809191"},{"key":"12_CR35","unstructured":"H. Sawada, S. Araki, R. Mukai and S. Makino, \u201cBlind extraction of a dominant source from mixtures of many sources using ICA and time-frequency masking,\u201d in ISCAS 2005, pp. 5882\u20135885, May 2005."},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"N. Mitianoudis, and M. E. Davies, \u201cAudio source separation of convolutive mixtures.\u201d in: IEEE Transactions on Audio and Speech Processing, vol 11(5), pp. 489-497, 2003.","DOI":"10.1109\/TSA.2003.815820"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"D. Kolossa and R. Orglmeister, \u201cNonlinear post-processing for blind speech separation,\u201d in Proc. ICA (LNCS 3195), Sep. 2004, pp. 832-839.","DOI":"10.1007\/978-3-540-30110-3_105"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Y. Ephraim and D. Malah, \u201cSpeech enhancement using a minimum mean square error log-spectral amplitude estimator,\u201d IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-33, pp. 443\u2013445, Apr. 1985.","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"S. Araki, S. Makino, Y. Hinamoto, R. Mukai, T. Nishikawa, and H. Saruwatari, \u201cEquivalence between frequency-domain blind source separation and frequency-domain adaptive beamforming for convolutivemixtures,\u201d in EURASIP Journal on Applied Signal Processing, vol. 11, p. 1157\u20131166, 2003.","DOI":"10.1155\/S1110865703305074"},{"key":"12_CR40","doi-asserted-by":"crossref","unstructured":"E. Hoffmann, D. Kolossa and R. Orglmeister, \u201cA batch algorithm for blind source separation of acoustic signals using ICA and time-frequency masking,\u201d in Proc. ICA (LNCS 4666), Sep. 2007, pp. 480\u2013488.","DOI":"10.1007\/978-3-540-74494-8_60"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"D. Kolossa, A. Klimas and R. Orglmeister, \u201cSeparation and robust recognition of noisy, convolutive speech mixtures using time-frequency masking and missing data techniques,\u201d in IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), pp. 82\u201385, New Paltz, NY, 2005.","DOI":"10.1109\/ASPAA.2005.1540174"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"E. Hoffmann, D. Kolossa, and R. Orglmeister, \u201cA soft masking strategy based on multichannel speech probability estimation for source separation and robust speech recognition\u201d, In: Proc. WASPAA, New Paltz, NY, 2007.","DOI":"10.1109\/ASPAA.2007.4393002"},{"key":"12_CR43","doi-asserted-by":"crossref","unstructured":"R. J. McAulay and M. L. Malpass, \u201cSpeech enhancement using a soft-decision noise suppression filter,\u201d IEEE Trans.\u00a0ASSP-28, pp. 137\u2013145, Apr. 1980.","DOI":"10.1109\/TASSP.1980.1163394"},{"key":"12_CR44","unstructured":"I. Cohen, \u201cOn speech Enhancement under signal presence uncertainty,\u201d International Conference on Acoustic and Speech Signal Processing, pp. 167\u2013170, May 2001."},{"key":"12_CR45","unstructured":"Y. Ephraim and I. Cohen, \u201cRecent advancements in speech enhancement\u201d, The Electrical Engineering Handbook, CRC Press, 2006."},{"key":"12_CR46","unstructured":"R. G. Leonard, \u201cA database for speaker-independent digit recognition\u201d, Proc. ICASSP 84, Vol. 3, p. 42.11, 1984."},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"S. Srinivasan and D. Wang, \u201cTransforming binary uncertainties for robust speech recognition\u201d, in IEEE Trans. Audio, Speech and Language Processing, IEEE Transactions on Speech and Audio Processing vol. 15, pp. 2130\u20132140, 2007.","DOI":"10.1109\/TASL.2007.901836"},{"key":"12_CR48","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/JSTSP.2010.2057194","volume":"4","author":"RF Astudillo","year":"2010","unstructured":"R. F. Astudillo, D. Kolossa, P. Mandelartz and R. Orglmeister, \u201cAn uncertainty propagation approach to robust ASR using the ETSI advanced front-end\u201d, IEEE Journal of Selected Topics in Signal Processing, vol. 4, pp. 824\u2013833, 2010.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"12_CR49","doi-asserted-by":"crossref","unstructured":"G. Brown and D. Wang, \u201cSeparation of speech by computational auditory scene analysis\u201d, Speech Enhancement, eds. J. Benesty, S. Makino and J. Chen, Springer, pp. 371\u2013402, 2005.","DOI":"10.1007\/3-540-27489-8_16"},{"key":"12_CR50","doi-asserted-by":"crossref","unstructured":"R. F. Astudillo, D. Kolossa and R. Orglmeister, \u201cPropagation of statistical information through non-linear feature extractions for robust speech recognition\u201d, in Proc. MaxEnt, 2007.","DOI":"10.1063\/1.2821269"},{"key":"12_CR51","unstructured":"S. Young, G. Evermann, T. Hain, D. Kershaw, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, P. Woodland, \u201cThe HTK Book (for HTK Version 3.4)\u201d, Cambridge University Engineering Department, 2006."}],"container-title":["Robust Speech Recognition of Uncertain or Missing Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-21317-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T02:00:33Z","timestamp":1741312833000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-642-21317-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642213168","9783642213175"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-21317-5_12","relation":{},"subject":[],"published":{"date-parts":[[2011]]},"assertion":[{"value":"23 June 2011","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}