{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T05:27:38Z","timestamp":1738387658381,"version":"3.35.0"},"publisher-location":"Berlin, Heidelberg","reference-count":23,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540858522"},{"type":"electronic","value":"9783540858539"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-85853-9_10","type":"book-chapter","created":{"date-parts":[[2008,8,30]],"date-time":"2008-08-30T09:27:54Z","timestamp":1220088474000},"page":"110-118","source":"Crossref","is-referenced-by-count":0,"title":["A Neural Network Based Regression Approach for Recognizing Simultaneous Speech"],"prefix":"10.1007","author":[{"given":"Weifeng","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenichi","family":"Kumatani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Dines","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathew","family":"Magimai-Doss","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Herv\u00e9","family":"Bourlard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"10_CR1","volume-title":"Blind source seperation","author":"S. Haykin","year":"2000","unstructured":"Haykin, S.: Unsupervised adaptive filtering. Blind source seperation, vol.\u00a01. Wiley, New York (2000)"},{"issue":"8","key":"10_CR2","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1109\/PROC.1972.8817","volume":"60","author":"O.L. Frost","year":"1972","unstructured":"Frost, O.L.: An algorithm for linearly constrained adaptive array processing. Proc. IEEE\u00a060(8), 926\u2013935 (1972)","journal-title":"Proc. IEEE"},{"issue":"1","key":"10_CR3","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1109\/TAP.1982.1142739","volume":"30","author":"L.J. Griffiths","year":"1982","unstructured":"Griffiths, L.J., Jim, C.W.: An Alternative Approach to Linearly Constrained Adaptive Beamforming. IEEE Trans. on Antennas and Propagation\u00a0AP-30(1), 27\u201334 (1982)","journal-title":"IEEE Trans. on Antennas and Propagation"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Moore, D., McCowan, I.: Microphone array speech recognition: Experiments on overlapping speech in meetings. In: Proc. ICASSP, pp. 497\u2013500 (2003)","DOI":"10.1109\/ICASSP.2003.1200015"},{"key":"10_CR5","series-title":"Lecture Notes in Computer Science","volume-title":"The SRI-ICSI Spring 2007 Meeting and Lecture Recognition System","author":"A. Stolcke","year":"2007","unstructured":"Stolcke, A., et al.: The SRI-ICSI Spring 2007 Meeting and Lecture Recognition System. LNCS. Springer, Heidelberg (2007)"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Cetin, O., Shriberg, E.: Speaker overlaps and ASR errors in meetings: Effects before, during, and after the overlap. In: Proc. ICASSP, vol.\u00a01, pp. 357\u2013360 (2006)","DOI":"10.1109\/ICASSP.2006.1660031"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Hain, T., Burget, L., Dines, J., Garau, G., Wan, V., Karafiat, M., Vepa, J., Lincoln, M.: The AMI system for the transcription of speech in meetings. In: Proc. ICASSP, Honolulu, Hawaii (2007)","DOI":"10.1109\/ICASSP.2007.366923"},{"key":"10_CR8","unstructured":"Li, W., Magimai.-Doss, M., Dines, J., Bourlard, H.: MLP-based log spectral energy mapping for robust overlapping speech recognition, IDIAP Technical Report, 07-54 (2007)"},{"key":"10_CR9","unstructured":"Young, S., et al.: The HTK Book, Version 3.4., http:\/\/htk.eng.cam.ac.uk\/docs\/docs.shtml"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Li, W., Dines, J., Magimai.-Doss, M., Bourlard, H.: Neural Network based Regression for Robust Overlapping Speech Recognition using Microphone Arrays, IDIAP Technical Report 08-09 (2008)","DOI":"10.21437\/Interspeech.2008-321"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Lincoln, M., McCowan, I., Vepa, I., Maganti, H.K.: The multichannel Wall Street Journal audio visual corpus ( mc-wsj-av): Specification and initial experiments. In: Proc. ASRU, pp. 357\u2013362 (2005)","DOI":"10.1109\/ASRU.2005.1566470"},{"key":"10_CR12","unstructured":"Gehrig, T., McDonough, J.: Tracking and far-field speech recognition for multiple simultaneous speakers. In: Proc. the Workshop on Machine Learning and Multimodal Interaction (September 2006)"},{"key":"10_CR13","doi-asserted-by":"publisher","first-page":"2527","DOI":"10.1109\/TASL.2007.907430","volume":"15","author":"K. Kumatani","year":"2007","unstructured":"Kumatani, K., Gehrig, T., Mayer, U., Stoimenov, E., McDonough, J., W\u00f6lfel, M.: Adaptive beamforming with a minimum mutual information criterion. IEEE Transactions on Audio, Speech and Language Processing\u00a015, 2527\u20132541 (2007)","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"10_CR14","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/1-4020-7769-6_10","volume-title":"Audio Signal Processing for Next-Generation Multimedia Communication Systems","author":"H. Buchner","year":"2004","unstructured":"Buchner, H., Aichner, R., Kellermann, W.: Blind source seperation for convolutive mixtures: A unified treatment. In: Audio Signal Processing for Next-Generation Multimedia Communication Systems, pp. 255\u2013289. Kluwer Academic, Boston (2004)"},{"key":"10_CR15","doi-asserted-by":"crossref","DOI":"10.1002\/0471221104","volume-title":"Optimum Array Processing","author":"H.L. Trees Van","year":"2002","unstructured":"Van Trees, H.L.: Optimum Array Processing. Wiley-Interscience, New York (2002)"},{"key":"10_CR16","unstructured":"Werbos, P.J.: Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences, PhD Thesis. Harvard University, Cambridge, MA (1974)"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Sorensen, H.B.D.: A cepstral noise reductionmulti-layer neural network. In: Proc. ICASSP, vol.\u00a02, pp. 933\u2013936 (1991)","DOI":"10.1109\/ICASSP.1991.150493"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Yuk, D., Flanagan, J.: Telephone speech recognition using neural networks and hiddenMarkov models. In: Proc. ICASSP, vol.\u00a01, pp. 157\u2013160 (1999)","DOI":"10.1109\/ICASSP.1999.758086"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Che, C., Lin, Q., Pearson, J., de Vries, B., Flanagan, J.: Microphone arrays and neural networks for robust speech recognition. In: Proc. the workshop on Human Language Technology, pp. 342\u2013347 (1994)","DOI":"10.3115\/1075812.1075891"},{"key":"10_CR20","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1007\/978-3-662-04619-7_3","volume-title":"Microphone Arrays","author":"K. Uwe Simmer","year":"2001","unstructured":"Uwe Simmer, K., Bitzer, J., Marro, C.: Post-filtering techniques. In: Brandstein, M., Ward, D. (eds.) Microphone Arrays, ch.\u00a03, pp. 39\u201360. Springer, Heidelberg (2001)"},{"key":"10_CR21","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: Proc. the IEEE International Conference on Multimedia and Expo (ICME) (July 2005)","DOI":"10.1109\/ICME.2005.1521688"},{"key":"10_CR22","volume-title":"Fundamentals of Speech Recognition","author":"L.R. Rabiner","year":"1993","unstructured":"Rabiner, L.R., Juang, B.H.: Fundamentals of Speech Recognition. Prentice-Hall, Englewood Cliffs (1993)"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Lin, Q., Che, C., Yuk, D.-S., Jin, L., de Vries, B., Pearson, J., Flanagan, J.: Robust distant-talking speech recognition. In: Proc. ICASSP, vol.\u00a01, pp. 21\u201324 (1996)","DOI":"10.1109\/ICASSP.1996.540280"}],"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\/978-3-540-85853-9_10.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T19:05:46Z","timestamp":1738350346000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-85853-9_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540858522","9783540858539"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-85853-9_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[]}}