{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T22:55:37Z","timestamp":1756076137610,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319218335"},{"type":"electronic","value":"9783319218342"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-21834-2_16","type":"book-chapter","created":{"date-parts":[[2016,4,20]],"date-time":"2016-04-20T15:06:28Z","timestamp":1461164788000},"page":"179-192","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Turbo-Decoding Weighted Forward-Backward Algorithm for Multimodal Speech Recognition"],"prefix":"10.1007","author":[{"given":"Simon","family":"Receveur","sequence":"first","affiliation":[]},{"given":"David","family":"Scheler","sequence":"additional","affiliation":[]},{"given":"Tim","family":"Fingscheidt","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,4,21]]},"reference":[{"issue":"2","key":"16_CR1","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1109\/TIT.1974.1055186","volume":"20","author":"L Bahl","year":"1974","unstructured":"Bahl L, Cocke J, Jelinek F, Raviv J (1974) Optimal decoding of linear codes for minimizing symbol error rate. IEEE Trans Inf Theory 20(2):284\u2013287. doi:10.1109\/TIT.1974.1055186","journal-title":"IEEE Trans Inf Theory"},{"key":"16_CR2","doi-asserted-by":"publisher","unstructured":"Berrou C, Glavieux A, Thitimajshima P (1993) Near Shannon limit error-correcting coding and decoding: turbo-codes. In: Proceedings of IEEE International conference on communications (ICC 1993), Geneva, Switzerland, pp 1064\u20131070. doi:10.1109\/ICC.1993.397441","DOI":"10.1109\/ICC.1993.397441"},{"key":"16_CR3","doi-asserted-by":"publisher","unstructured":"Bourlard H, Dupont S (1996) A new ASR approach based on independent processing and recombination of partial frequency bands. In: Proceedings of 4th international conference on spoken language processing (ICSLP 1996), Philadelphia, PA, USA, pp 426\u2013429. doi:10.1109\/ICSLP.1996.607145","DOI":"10.1109\/ICSLP.1996.607145"},{"issue":"10","key":"16_CR4","doi-asserted-by":"publisher","first-page":"1727","DOI":"10.1109\/26.957394","volume":"49","author":"S ten Brink","year":"2001","unstructured":"ten Brink S (2001) Convergence behavior of iteratively decoded parallel concatenated codes. IEEE Trans Commun 49(10):1727\u20131737. doi:10.1109\/26.957394","journal-title":"IEEE Trans Commun"},{"issue":"5","key":"16_CR5","doi-asserted-by":"publisher","first-page":"2421","DOI":"10.1121\/1.2229005","volume":"120","author":"M Cooke","year":"2006","unstructured":"Cooke M, Barker J, Cunningham S, Shao X (2006) An audio-visual corpus for speech perception and automatic speech recognition. J. Acoust Soc Am 120(5):2421\u20132424","journal-title":"J. Acoust Soc Am"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Garg A, Potamianos G, Neti C, Huang T (2003) Frame-dependent multi-stream reliability indicators for audio-visual speech recognition. In: Proceedings of international conference on multimedia and expo (ICME 2003), Baltimore, MD, USA, pp 605\u2013608","DOI":"10.1109\/ICME.2003.1221384"},{"issue":"4","key":"16_CR7","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1109\/89.326616","volume":"2","author":"H Hermansky","year":"1994","unstructured":"Hermansky H, Morgan N (1994) RASTA processing of speech. IEEE Trans Speech Audio Process 2(4):578\u2013589","journal-title":"IEEE Trans Speech Audio Process"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Hermansky H, Tibrewala S, Pavel M (1996) Towards ASR on partially corrupted speech. In: Proceedings of 4th international conference on spoken language (ICSLP 1996), Philadelphia, PA, USA, pp 462\u2013465","DOI":"10.21437\/ICSLP.1996-123"},{"key":"16_CR9","unstructured":"ITU-T: Rec. P.56 (2011) Objective measurement of active speech level. Int Telecommun Union (2011)"},{"key":"16_CR10","unstructured":"Jain U, Siegler MA, Doh SJ, Gouvea E, Huerta J, Moreno PJ, Raj B, Stern RM (1996) Recognition of continuous broadcast news with multiple unknown speakers and environments. In: Proceedings of ARPA speech recognition workshop. Harriman, NY, USA, pp 61\u201366"},{"issue":"12","key":"16_CR11","doi-asserted-by":"publisher","first-page":"2133","DOI":"10.1109\/TCOMM.2006.885050","volume":"54","author":"Jrg Kliewer","year":"2006","unstructured":"Kliewer J, Ng SX, Hanzo L (2006) Efficient computation of EXIT functions for nonbinary iterative decoding. IEEE Trans Commun 54(12):2133\u20132136. doi:10.1109\/TCOMM.2006.885050","journal-title":"IEEE Transactions on Communications"},{"key":"16_CR12","unstructured":"Kolossa D, Zeiler S, Vorwerk A, Orglmeister R (2009) Audiovisual speech recognition with missing or unreliable data. In: Proceedings of international conference on auditory-visual speech processing (AVSP 2009), Norwich, UK, pp 117\u2013122"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Kratt J, Metze F, Stiefelhagen R, Waibel A (2004) Large vocabulary audio-visual speech recognition using the janus speech recognition toolkit. In: Proceedings of DAGM-symposium, T\u00fcbingen, Germany, pp 488\u2013495","DOI":"10.1007\/978-3-540-28649-3_60"},{"key":"16_CR14","doi-asserted-by":"publisher","unstructured":"Luettin J, Potamianos G, Neti C (2001) Asynchronous stream modeling for large vocabulary audio-visual speech recognition. In: edings of international conference on acoustics speech and signal processing (ICASSP 2001), Salt Lake City, UT, USA, pp 169\u2013172. doi:10.1109\/ICASSP.2001.940794","DOI":"10.1109\/ICASSP.2001.940794"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Ming J, Hanna P, Stewart D, Owens M, Smith FJ (1999) Improving speech recognition performance by using multi-model approaches. In: Proceedings of IEEE international conference on acoustics, speech, and signal processing (ICASSP 1999), Phoenix, AZ, USA, pp 161\u2013164","DOI":"10.1109\/ICASSP.1999.758087"},{"issue":"1","key":"16_CR16","doi-asserted-by":"publisher","first-page":"1274","DOI":"10.1155\/S1110865702206083","volume":"11","author":"AV Nefian","year":"2002","unstructured":"Nefian AV, Liang L, Pi X, Liu X, Murphy K (2002) Dynamic Bayesian networks for audio-visual speech recognition. EURASIP J Appl Signal Process 11(1):1274\u20131288","journal-title":"EURASIP J Appl Signal Process"},{"key":"16_CR17","unstructured":"Neti C, Potamianos G, Luettin J, Matthews I, Glotin H, Vergyri D, Sison J, Mashari A, Zhou J (2000) Audio-visual speech recognition. Technical report, center lang speech process, Johns Hopkins University, Baltimore, MD, USA"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Potamianos G, Neti C, Iyengar G, Helmuth E (2001) Large-vocabulary audio-visual speech recognition by machines and humans. In: Proceedings of Eurospeech, Aalborg, Denmark, pp 1027\u20131030","DOI":"10.21437\/Eurospeech.2001-294"},{"key":"16_CR19","first-page":"356","volume-title":"Issues in visual and audio-visual speech processing","author":"G Potamianos","year":"2004","unstructured":"Potamianos G, Neti C, Luettin J, Matthews I (2004) Audio-visual automatic speech recognition: an overview. In: Bailly G, Vatikiotis-Bateson E, Perrier P (eds) Issues in visual and audio-visual speech processing. MIT Press, Cambridge, pp 356\u2013396"},{"key":"16_CR20","unstructured":"Rogozan A, Del\u00e9glise P, Alissali M (1997) Adaptive determination of audio and visual weights for automatic speech recognition. In: Proceedings of European tutorial workshop on audio-visual speech processing, Rhodes, Greece, pp 61\u201364"},{"key":"16_CR21","unstructured":"Scheler D, Walz S, Fingscheidt T (2012) On iterative exchange of soft state information in two-channel automatic speech recognition. In: Proceedings of 10th ITG conference on speech communication, Braunschweig, Germany, pp 55\u201358"},{"key":"16_CR22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2008\/478396","volume":"2008","author":"ST Shivappa","year":"2007","unstructured":"Shivappa ST, Rao BD, Trivedi MM (2007) An iterative decoding algorithm for fusion of multimodal information. EURASIP J Adv Signal Process 2008:1\u201310","journal-title":"EURASIP J Adv Signal Process"},{"key":"16_CR23","doi-asserted-by":"publisher","unstructured":"Shivappa ST, Rao BD, Trivedi MM (2008) Multimodal information fusion using the iterative decoding algorithm and its application to audio-visual speech recognition. In: Proceedings of IEEE international conference on acoustics, speech, and signal processing (ICASSP 2008), Las Vegas, NV, USA, pp 2241\u20132244. doi:10.1109\/ICASSP.2008.4518091","DOI":"10.1109\/ICASSP.2008.4518091"},{"key":"16_CR24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-13015-5","volume-title":"Speechreading by humans and machines","author":"DG Stork","year":"1996","unstructured":"Stork DG, Hennecke ME, Prasad KV (1996) Visionary speech: looking ahead to practical speechreading systems. In: Stork DG, Hennecke ME (eds) Speechreading by humans and machines. Springer, Berlin"},{"issue":"2","key":"16_CR25","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1121\/1.1907309","volume":"26","author":"WH Sumby","year":"1954","unstructured":"Sumby WH, Pollack I (1954) Visual contribution to speech intelligibility in noise. J Acoust Soc Am 26(2):212\u2013215. doi:10.1121\/1.1907309","journal-title":"J Acoust Soc Am"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Tomlinson MJ, Russell MJ, Brooke NM (1996) Integrating audio and visual information to provide highly robust speech recognition. In: Proceedings of IEEE international conference on acoustics, speech and signal processing (ICASSP 1996), Atlanta, GA, USA, pp 821\u2013824","DOI":"10.1109\/ICASSP.1996.543247"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Varga P, Moore RK (1990) Hidden Markov model decomposition of speech and noise. In Proceedings of IEEE international conference on acoustics, speech, and signal processing (ICASSP 1990), Albuquerque, NM, USA, pp 845\u2013848","DOI":"10.1109\/ICASSP.1990.115970"}],"container-title":["Signals and Communication Technology","Situated Dialog in Speech-Based Human-Computer Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-21834-2_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T14:48:06Z","timestamp":1676990886000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-21834-2_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319218335","9783319218342"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-21834-2_16","relation":{},"ISSN":["1860-4862","1860-4870"],"issn-type":[{"type":"print","value":"1860-4862"},{"type":"electronic","value":"1860-4870"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"21 April 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}