{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T13:31:59Z","timestamp":1760707919485},"publisher-location":"Berlin, Heidelberg","reference-count":31,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540781547"},{"type":"electronic","value":"9783540781554"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-78155-4_25","type":"book-chapter","created":{"date-parts":[[2008,2,21]],"date-time":"2008-02-21T12:46:47Z","timestamp":1203598007000},"page":"283-294","source":"Crossref","is-referenced-by-count":3,"title":["To Separate Speech"],"prefix":"10.1007","author":[{"given":"John","family":"McDonough","sequence":"first","affiliation":[]},{"given":"Kenichi","family":"Kumatani","sequence":"additional","affiliation":[]},{"given":"Tobias","family":"Gehrig","sequence":"additional","affiliation":[]},{"given":"Emilian","family":"Stoimenov","sequence":"additional","affiliation":[]},{"given":"Uwe","family":"Mayer","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Schacht","sequence":"additional","affiliation":[]},{"given":"Matthias","family":"W\u00f6lfel","sequence":"additional","affiliation":[]},{"given":"Dietrich","family":"Klakow","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Gehrig, T., Klee, U., McDonough, J., Ikbal, S., W\u00f6lfel, M., F\u00fcgen, C.: Tracking and beamforming for multiple simultaneous speakers with probabilistic data association filters. In: Proc. Interspeech, pp. 2594\u20132597 (2006)","DOI":"10.21437\/Interspeech.2006-650"},{"key":"25_CR2","volume-title":"Tracking and Data Association","author":"Y. Bar-Shalom","year":"1988","unstructured":"Bar-Shalom, Y., Fortmann, T.E.: Tracking and Data Association. Academic Press, San Diego (1988)"},{"key":"25_CR3","doi-asserted-by":"crossref","DOI":"10.1002\/0471221104","volume-title":"Optimum Array Processing","author":"H.L. Van Trees","year":"2002","unstructured":"Van Trees, H.L.: Optimum Array Processing. Wiley-Interscience, Chichester (2002)"},{"key":"25_CR4","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.: Independent component analysis: Algorithms and applications. Neural Networks\u00a013, 411\u2013430 (2000)","journal-title":"Neural Networks"},{"key":"25_CR5","unstructured":"McDonough, J., Kumatani, K.: Minimum mutual information beamforming. Technical Report 107, Interactive Systems Lab, Universit\u00e4t Karlsruhe (August 2006)"},{"key":"25_CR6","unstructured":"Kumatani, K., Gehrig, T., Mayer, U., Stoimenov, E., McDonough, J., W\u00f6lfel, M.: Adaptive beamforming with a minimum mutual information criterion. IEEE Trans. Audio Speech and Lang. Proc. (to appear)"},{"key":"25_CR7","volume-title":"Multirate Systems and Filter Banks","author":"P.P. Vaidyanathan","year":"1993","unstructured":"Vaidyanathan, P.P.: Multirate Systems and Filter Banks. Prentice-Hall, Englewood Cliffs (1993)"},{"issue":"1","key":"25_CR8","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TSA.2002.807353","volume":"11","author":"J.M. Haan de","year":"2003","unstructured":"de Haan, J.M., Grbic, N., Claesson, I., Nordholm, S.E.: Filter bank design for subband adaptive microphone arrays. IEEE Trans. Speech and Audio Proc.\u00a011(1), 14\u201323 (2003)","journal-title":"IEEE Trans. Speech and Audio Proc."},{"key":"25_CR9","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/0165-1684(87)90001-6","volume":"12","author":"H. Brehm","year":"1987","unstructured":"Brehm, H., Stammler, W.: Description and generation of spherically invariant speech-model signals. Signal Processing\u00a012, 119\u2013141 (1987)","journal-title":"Signal Processing"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Mohri, M., Riley, M., Hindle, D., Ljolje, A., Periera, F.: Full expansion of context-dependent networks in large vocabulary speech recognition. In: Proc. ICASSP, Seattle, vol.\u00a0II, pp. 665\u2013668 (1998)","DOI":"10.1109\/ICASSP.1998.675352"},{"key":"25_CR11","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1006\/csla.2001.0184","volume":"16","author":"M. Mohri","year":"2002","unstructured":"Mohri, M., Pereira, F., Riley, M.: Weighted finite-state transducers in speech recognition. Computer Speech and Language\u00a016, 69\u201388 (2002)","journal-title":"Computer Speech and Language"},{"key":"25_CR12","unstructured":"Mohri, M., Riley, M.: Network optimizations for large vocabulary speech recognition. Speech Communication\u00a025(3) (1998)"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Stoimenov, E., McDonough, J.: Modeling polyphone context with weighted finite-state transducers. In: Proc. ICASSP (2006)","DOI":"10.21437\/Interspeech.2007-423"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Stoimenov, E., McDonough, J.: Memory efficient modeling of polyphone context with weighted finite-state transducers. In: Proc. Interspeech (2007)","DOI":"10.21437\/Interspeech.2007-423"},{"key":"25_CR15","unstructured":"Mohri, M.: Finite-state transducers in language and speech processing. Computational Linguistics\u00a023(2) (1997)"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Mohri, M., Riley, M.: A weight pushing algorithm for large vocabulary speech recognition. In: Proc. ASRU, Aarlborg, Denmark, September 2001, pp. 1603\u20131606 (2001)","DOI":"10.21437\/Eurospeech.2001-390"},{"issue":"1\u20132","key":"25_CR17","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/S0304-3975(98)00115-7","volume":"234","author":"M. Mohri","year":"2000","unstructured":"Mohri, M.: Minimization algorithms for sequential transducers. Theoretical Computer Science\u00a0234(1\u20132), 177\u2013201 (2000)","journal-title":"Theoretical Computer Science"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Lincoln, M., McCowan, I., Vepa, J., Maganti, H.: The multi-channel wall street journal audio visual corpus (mc-wsj-av): specification and initial experiments. In: Proc. ASRU, pp. 357\u2013362 (November 2005)","DOI":"10.1109\/ASRU.2005.1566470"},{"issue":"5","key":"25_CR19","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/MSP.2005.1511829","volume":"22","author":"M. W\u00f6lfel","year":"2005","unstructured":"W\u00f6lfel, M., McDonough, J.: Minimum variance distortionless response spectral estimation, review and refinements. IEEE Signal Processing Magazine\u00a022(5), 117\u2013126 (2005)","journal-title":"IEEE Signal Processing Magazine"},{"key":"25_CR20","volume-title":"Introduction to Statistical Pattern Recognition","author":"K. Fukunaga","year":"1990","unstructured":"Fukunaga, K.: Introduction to Statistical Pattern Recognition. Academic Press, New York (1990)"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Gales, M.J.F.: Semi-tied covariance matrices. In: Proc. ICASSP (1998)","DOI":"10.1109\/ICASSP.1998.675350"},{"key":"25_CR22","unstructured":"Fransen, J., Pye, D., Robinson, T., Woodland, P., Young, S.: Wsjcam0 corpus and recording description. Technical Report CUED\/F-INFENG\/TR.192, Cambridge University Engineering Department (CUED) Speech Group (September 1994)"},{"key":"25_CR23","volume-title":"Discrete-Time Processing of Speech Signals","author":"J. Deller","year":"1993","unstructured":"Deller, J., Hansen, J., Proakis, J.: Discrete-Time Processing of Speech Signals. Macmillan Publishing, New York (1993)"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Anastasakos, T., McDonough, J., Schwarz, R., Makhoul, J.: A compact model for speaker-adaptive training. In: Proc. ICSLP, pp. 1137\u20131140 (1996)","DOI":"10.1109\/ICSLP.1996.607807"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Uebel, L., Woodland, P.: Improvements in linear transform based speaker adaptation. In: Proc. ICASSP (2001)","DOI":"10.1109\/ICASSP.2001.940764"},{"key":"25_CR26","unstructured":"W\u00f6lfel, M.: Mel-Frequenzanpassung der Minimum Varianz Distortionless Response Einh\u00fcllenden. In: Proc. of ESSV (2003)"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Gales, M.J.F.: Maximum likelihood linear transformations for HMM-based speech recognition. Computer Speech and Language\u00a012 (1998)","DOI":"10.1006\/csla.1998.0043"},{"key":"25_CR28","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1006\/csla.1995.0010","volume":"9","author":"C.J. Leggetter","year":"1995","unstructured":"Leggetter, C.J., Woodland, P.C.: Maximum likelihood linear regression for speaker adaptation of continuous density hidden markov models. Computer Speech and Language\u00a09, 171\u2013185 (1995)","journal-title":"Computer Speech and Language"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"McDonough, J., Stoimenov, E., Klakow, D.: An algorithm for fast composition of weighted finite-state transducers. In: Proc. ASRU (submitted, 2007)","DOI":"10.1109\/ASRU.2007.4430156"},{"key":"25_CR30","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1007\/978-3-662-04619-7_3","volume-title":"Microphone Arrays","author":"K.U. Simmer","year":"2001","unstructured":"Simmer, K.U., Bitzer, J., Marro, C.: Post-filtering techniques. In: Branstein, M., Ward, D. (eds.) Microphone Arrays, pp. 39\u201360. Springer, Heidelberg (2001)"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"McCowan, I., Hari-Krishna, M., Gatica-Perez, D., Moore, D., Ba, S.: Speech acquisition in meetings with an audio-visual sensor array. In: Proceedings of the IEEE International Conference on Multimedia and Expo (ICME) (July 2005)","DOI":"10.1109\/ICME.2005.1521688"}],"container-title":["Lecture Notes in Computer Science","Machine Learning for Multimodal Interaction"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-78155-4_25.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T15:50:25Z","timestamp":1684252225000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-78155-4_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540781547","9783540781554"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-78155-4_25","relation":{},"subject":[]}}