{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,20]],"date-time":"2024-07-20T05:59:53Z","timestamp":1721455193747},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2014,4,5]],"date-time":"2014-04-05T00:00:00Z","timestamp":1396656000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["EURASIP J. Adv. Signal Process."],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1186\/1687-6180-2014-47","type":"journal-article","created":{"date-parts":[[2014,4,7]],"date-time":"2014-04-07T19:53:06Z","timestamp":1396900386000},"source":"Crossref","is-referenced-by-count":4,"title":["Audio visual speech source separation via improved context dependent association model"],"prefix":"10.1186","volume":"2014","author":[{"given":"Alireza","family":"Kazemi","sequence":"first","affiliation":[]},{"given":"Reza","family":"Boostani","sequence":"additional","affiliation":[]},{"given":"Fariborz","family":"Sobhanmanesh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,4,5]]},"reference":[{"key":"621_CR1","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1121\/1.1907309","volume":"26","author":"WH Sumby","year":"1954","unstructured":"Sumby WH, Pollack I: Visual contribution to speech intelligibility in noise. J. Acoust. Soc. Am 1954, 26: 212-215. 10.1121\/1.1907309","journal-title":"J. Acoust. Soc. Am"},{"issue":"1273","key":"621_CR2","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1098\/rstb.1992.0009","volume":"335","author":"Q Summerfield","year":"1992","unstructured":"Summerfield Q: Lipreading and audio-visual speech perception. Philos. Trans. R. Soc. Lond. B Biol. Sci 1992, 335(1273):71-78. 10.1098\/rstb.1992.0009","journal-title":"Philos. Trans. R. Soc. Lond. B Biol. Sci"},{"key":"621_CR3","doi-asserted-by":"publisher","first-page":"1197","DOI":"10.1121\/1.1288668","volume":"108","author":"KW Grant","year":"2000","unstructured":"Grant KW, Seitz P-F: The use of visible speech cues for improving auditory detection of spoken sentences. J. Acoust. Soc. Am 2000, 108: 1197. 10.1121\/1.1288668","journal-title":"J. Acoust. Soc. Am"},{"issue":"5588","key":"621_CR4","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1038\/264746a0","volume":"264","author":"H McGurk","year":"1976","unstructured":"McGurk H, MacDonald J: Hearing lips and seeing voices. Nature 1976, 264(5588):746-748. 10.1038\/264746a0","journal-title":"Nature"},{"issue":"2","key":"621_CR5","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.cognition.2004.01.006","volume":"93","author":"J-L Schwartz","year":"2004","unstructured":"Schwartz J-L, Berthommier F, Savariaux C: Seeing to hear better: evidence for early audio-visual interactions in speech identification. Cognition 2004, 93(2):69-78. 10.1016\/j.cognition.2004.01.006","journal-title":"Cognition"},{"key":"621_CR6","volume-title":"Automatic lipreading to enhance speech recognition","author":"ED Petajan","year":"1984","unstructured":"Petajan ED: Automatic lipreading to enhance speech recognition. PhD thesis, University of Illinois, Illinois; 1984."},{"issue":"6","key":"621_CR7","doi-asserted-by":"publisher","first-page":"3007","DOI":"10.1121\/1.1358887","volume":"109","author":"L Girin","year":"2001","unstructured":"Girin L, Schwartz J-L, Feng G: Audio-visual enhancement of speech in noise. J. Acoust. Soc. Am 2001, 109(6):3007-3020. 10.1121\/1.1358887","journal-title":"J. Acoust. Soc. Am"},{"key":"621_CR8","first-page":"1449","volume-title":"Proceedings of the ISCA International Conference on Spoken Language Processing (ICSLP\u201902)","author":"S Deligne","year":"2002","unstructured":"Deligne S, Potamianos G, Neti C: Audio-visual speech enhancement with AVCDCN (AudioVisual Code-book Dependent Cepstral Normalization). In Proceedings of the ISCA International Conference on Spoken Language Processing (ICSLP\u201902). ISCA; 2002:1449-1452."},{"key":"621_CR9","first-page":"1045","volume-title":"Proceedings of the ISCA European Conference on Speech Communication and Technology (EUROSPEECH\u201903)","author":"F Berthommier","year":"2002","unstructured":"Berthommier F: Audiovisual speech enhancement based on the association between speech envelope and video features. In Proceedings of the ISCA European Conference on Speech Communication and Technology (EUROSPEECH\u201903). ISCA; 2002:1045-1048."},{"key":"621_CR10","first-page":"2025","volume-title":"Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201902)","author":"R Goecke","year":"2002","unstructured":"Goecke R, Potamianos G, Neti C: Noisy audio feature enhancement using audio-visual speech data. In Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201902). IEEE; 2002:2025-2028."},{"issue":"7","key":"621_CR11","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1016\/j.specom.2007.04.008","volume":"49","author":"B Rivet","year":"2007","unstructured":"Rivet B, Girin L, Jutten C: Visual voice activity detection as a help for speech source separation from convolutive mixtures. Speech Communication 2007, 49(7):667-677.","journal-title":"Speech Communication"},{"issue":"1","key":"621_CR12","first-page":"1164","volume":"2002","author":"D Sodoyer","year":"2002","unstructured":"Sodoyer D, Schwartz J-L, Girin L, Klinkisch J, Jutten C: Separation of audio-visual speech sources: a new approach exploiting the audio-visual coherence of speech stimuli. EURASIP J. Appl. Signal Process 2002, 2002(1):1164-1173.","journal-title":"EURASIP J. Appl. Signal Process"},{"key":"621_CR13","first-page":"657","volume-title":"Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201904)","author":"S Rajaram","year":"2004","unstructured":"Rajaram S, Nefian AV, Huang TS: Bayesian separation of audio-visual speech sources. In Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201904). IEEE; 2004:657-661."},{"issue":"1","key":"621_CR14","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.specom.2004.10.002","volume":"44","author":"D Sodoyer","year":"2004","unstructured":"Sodoyer D, Girin L, Jutten C, Schwartz J-L: Developing an audio-visual speech source separation algorithm. Speech Commun 2004, 44(1):113-125.","journal-title":"Speech Commun"},{"key":"621_CR15","first-page":"425","volume-title":"Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201905)","author":"W Wang","year":"2005","unstructured":"Wang W, Cosker D, Hicks Y, Sanei S, Chambers J: Video assisted speech source separation. In Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201905). IEEE; 2005:425-425."},{"issue":"1","key":"621_CR16","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/TASL.2006.872619","volume":"15","author":"B Rivet","year":"2007","unstructured":"Rivet B, Girin L, Jutten C: Mixing audiovisual speech processing and blind source separation for the extraction of speech signals from convolutive mixtures. Audio, Speech, Lang. Process. IEEE Trans 2007, 15(1):96-108.","journal-title":"Audio, Speech, Lang. Process. IEEE Trans"},{"key":"621_CR17","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1109\/MLSP.2007.4414315","volume-title":"IEEE Workshop On Machine Learning for Signal Processing (MLSP\u201907)","author":"C Sigg","year":"2007","unstructured":"Sigg C, Fischer B, Ommer B, Roth V, Buhmann J: Nonnegative CCA for audiovisual source separation. In IEEE Workshop On Machine Learning for Signal Processing (MLSP\u201907). IEEE; 2007:253-258."},{"key":"621_CR18","doi-asserted-by":"publisher","first-page":"1841","DOI":"10.1109\/ICASSP.2008.4517991","volume-title":"IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201908)","author":"AL Casanovas","year":"2008","unstructured":"Casanovas AL, Monaci G, Vandergheynst P, Gribonval R: Blind audiovisual separation based on redundant representations. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201908). IEEE; 2008:1841-1844."},{"key":"621_CR19","volume-title":"EURASIP European Signal Processing Conference (EUSIPCO \u201908)","author":"G Monaci","year":"2008","unstructured":"Monaci G, Sommer F, Vandergheynst P: Learning sparse generative models of audiovisual signals. In EURASIP European Signal Processing Conference (EUSIPCO \u201908). EURASIP; 2008."},{"issue":"12","key":"621_CR20","doi-asserted-by":"publisher","first-page":"1898","DOI":"10.1109\/TNN.2009.2032182","volume":"20","author":"G Monaci","year":"2009","unstructured":"Monaci G, Vandergheynst P, Sommer FT: Learning bimodal structure in audio\u2013visual data. Neural Netw. IEEE Trans 2009, 20(12):1898-1910.","journal-title":"Neural Netw. IEEE Trans"},{"issue":"5","key":"621_CR21","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1109\/TMM.2010.2050650","volume":"12","author":"AL Casanovas","year":"2010","unstructured":"Casanovas AL, Monaci G, Vandergheynst P, Gribonval R: Blind audiovisual source separation based on sparse redundant representations. Multimedia, IEEE Trans 2010, 12(5):358-371.","journal-title":"Multimedia, IEEE Trans"},{"issue":"1","key":"621_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1687-6180-2012-1","volume":"2012","author":"Y Liang","year":"2012","unstructured":"Liang Y, Naqvi SM, Chambers JA: Audio video based fast fixed-point independent vector analysis for multisource separation in a room environment. EURASIP J. Adv. Signal Process 2012, 2012(1):1-16. 10.1186\/1687-6180-2012-1","journal-title":"EURASIP J. Adv. Signal Process"},{"key":"621_CR23","doi-asserted-by":"crossref","unstructured":"Liu Q, Wang W, Jackson PJ, Barnard M, Kittler J, Chambers JA: Source separation of convolutive and noisy mixtures using audio-visual dictionary learning and probabilistic time-frequency masking. IEEE Trans. Signal Process 2013., 61(22):","DOI":"10.1109\/TSP.2013.2277834"},{"issue":"9","key":"621_CR24","doi-asserted-by":"publisher","first-page":"1900","DOI":"10.1109\/TASL.2013.2261814","volume":"21","author":"MS Khan","year":"2013","unstructured":"Khan MS, Naqvi SM, Rehman A, Wang W, Chambers JA: Video-aided model-based source separation in real reverberant rooms. IEEE Trans. Audio Speech Lang. Process 2013, 21(9):1900-1912.","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"issue":"6","key":"621_CR25","doi-asserted-by":"publisher","first-page":"1129","DOI":"10.1162\/neco.1995.7.6.1129","volume":"7","author":"AJ Bell","year":"1995","unstructured":"Bell AJ, Sejnowski TJ: An information-maximization approach to blind separation and blind deconvolution. Neural Computat 1995, 7(6):1129-1159. 10.1162\/neco.1995.7.6.1129","journal-title":"Neural Computat"},{"issue":"7","key":"621_CR26","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1162\/neco.1997.9.7.1483","volume":"9","author":"A Hyv\u00e4rinen","year":"1997","unstructured":"Hyv\u00e4rinen A, Oja E: A fast fixed-point algorithm for independent component analysis. Neural Comput 1997, 9(7):1483-1492. 10.1162\/neco.1997.9.7.1483","journal-title":"Neural Comput"},{"issue":"1","key":"621_CR27","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1162\/089976699300016863","volume":"11","author":"J-F Cardoso","year":"1999","unstructured":"Cardoso J-F: High-order contrasts for independent component analysis. Neural Comput 1999, 11(1):157-192. 10.1162\/089976699300016863","journal-title":"Neural Comput"},{"key":"621_CR28","volume-title":"Speechreading (lipreading)","author":"J Jeffers","year":"1971","unstructured":"Jeffers J, Barley M: Speechreading (lipreading). Charles C. Thomas Publisher, Springfield, Illinois; 1971."},{"key":"621_CR29","first-page":"322","volume-title":"Proceedings of the International Conference on Pattern Recognition Applications and Methods (ICPRAM 2012)","author":"L Cappelletta","year":"2012","unstructured":"Cappelletta L, Harte N: Phoneme-to-viseme mapping for visual speech recognition. In Proceedings of the International Conference on Pattern Recognition Applications and Methods (ICPRAM 2012). IEEE; 2012:322-329."},{"issue":"1","key":"621_CR30","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/0165-1684(95)00042-C","volume":"45","author":"N Delfosse","year":"1995","unstructured":"Delfosse N, Loubaton P: Adaptive blind separation of independent sources: a deflation approach. Signal Process 1995, 45(1):59-83. 10.1016\/0165-1684(95)00042-C","journal-title":"Signal Process"},{"issue":"3","key":"621_CR31","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1109\/78.558482","volume":"45","author":"JK Tugnait","year":"1997","unstructured":"Tugnait JK: Identification and deconvolution of multichannel linear non-Gaussian, processes using higher order statistics and inverse filter criteria. Signal Process. IEEE Trans 1997, 45(3):658-672. 10.1109\/78.558482","journal-title":"Signal Process. IEEE Trans"},{"issue":"2","key":"621_CR32","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1109\/TNN.2009.2035920","volume":"21","author":"V Zarzoso","year":"2010","unstructured":"Zarzoso V, Comon P: Robust independent component analysis by iterative maximization of the kurtosis contrast with algebraic optimal step size. Neural Netw. IEEE Trans 2010, 21(2):248-261.","journal-title":"Neural Netw. IEEE Trans"},{"issue":"7","key":"621_CR33","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1109\/LSP.2003.813679","volume":"10","author":"S Gazor","year":"2003","unstructured":"Gazor S, Zhang W: Speech probability distribution. Signal Process. Lett. IEEE 2003, 10(7):204-207.","journal-title":"Signal Process. Lett. IEEE"},{"key":"621_CR34","volume-title":"Proc. Intl. Workshop on Acoustic, Echo, and Noise Control (IWAENC 2010)","author":"I Tashev","year":"2010","unstructured":"Tashev I, Acero A: Statistical modeling of the speech signal. In Proc. Intl. Workshop on Acoustic, Echo, and Noise Control (IWAENC 2010). IEEE; 2010."},{"issue":"4","key":"621_CR35","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1109\/LSP.2005.863638","volume":"13","author":"J Thomas","year":"2006","unstructured":"Thomas J, Deville Y, Hosseini S: Time-domain fast fixed-point algorithms for convolutive ICA. Signal Process. Lett. IEEE 2006, 13(4):228-231.","journal-title":"Signal Process. Lett. IEEE"},{"key":"621_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IranianMVIP.2010.5941132","volume-title":"Iranian Conference on Machine Vision and Image Processing (MVIP 2010)","author":"F Moayedi","year":"2010","unstructured":"Moayedi F, Kazemi A, Azimifar Z: Hidden Markov model-unscented Kalman filter contour tracking: a multi-cue and multi-resolution approach. In Iranian Conference on Machine Vision and Image Processing (MVIP 2010). IEEE, Piscataway; 2010:1-6."},{"issue":"1","key":"621_CR37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster AP, Laird NM, Rubin DB: Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Series B (Methodological) 1977, 39(1):1-38.","journal-title":"J. R. Stat. Soc. Series B (Methodological)"},{"issue":"6","key":"621_CR38","doi-asserted-by":"publisher","first-page":"989","DOI":"10.1109\/72.329697","volume":"5","author":"MT Hagan","year":"1994","unstructured":"Hagan MT, Menhaj M: Training feed-forward networks with the Marquardt algorithm. IEEE Trans. Neural Netw 1994, 5(6):989-993. 10.1109\/72.329697","journal-title":"IEEE Trans. Neural Netw"},{"issue":"4","key":"621_CR39","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"Vincent E, Gribonval R, F\u00e9votte C: Performance measurement in blind audio source separation. Audio, Speech, Lang. Process. IEEE Trans 2006, 14(4):1462-1469.","journal-title":"Audio, Speech, Lang. Process. IEEE Trans"}],"container-title":["EURASIP Journal on Advances in Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1687-6180-2014-47\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-6180-2014-47.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-6180-2014-47.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,22]],"date-time":"2019-01-22T01:23:02Z","timestamp":1548120182000},"score":1,"resource":{"primary":{"URL":"https:\/\/asp-eurasipjournals.springeropen.com\/articles\/10.1186\/1687-6180-2014-47"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4,5]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,12]]}},"alternative-id":["621"],"URL":"https:\/\/doi.org\/10.1186\/1687-6180-2014-47","relation":{},"ISSN":["1687-6180"],"issn-type":[{"value":"1687-6180","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,4,5]]},"article-number":"47"}}