{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:26:30Z","timestamp":1740122790154,"version":"3.37.3"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T00:00:00Z","timestamp":1641513600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T00:00:00Z","timestamp":1641513600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100003074","name":"agencia nacional de promoci\u00f3n cient\u00edfica y tecnol\u00f3gica","doi-asserted-by":"publisher","award":["PICT 2018-01802"],"award-info":[{"award-number":["PICT 2018-01802"]}],"id":[{"id":"10.13039\/501100003074","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009573","name":"universidad nacional de rosario","doi-asserted-by":"crossref","award":["ING610"],"award-info":[{"award-number":["ING610"]}],"id":[{"id":"10.13039\/100009573","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s10772-021-09944-7","type":"journal-article","created":{"date-parts":[[2022,1,7]],"date-time":"2022-01-07T00:03:47Z","timestamp":1641513827000},"page":"231-249","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Complementary models for audio-visual speech classification"],"prefix":"10.1007","volume":"25","author":[{"given":"Gonzalo D.","family":"Sad","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lucas D.","family":"Terissi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan C.","family":"G\u00f3mez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,7]]},"reference":[{"issue":"2","key":"9944_CR1","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1007\/s10772-012-9131-y","volume":"15","author":"RK Aggarwal","year":"2012","unstructured":"Aggarwal, R. K., & Dave, M. (2012). Integration of multiple acoustic and language models for improved Hindi speech recognition system. International Journal of Speech Technology, 15(2), 165\u2013180.","journal-title":"International Journal of Speech Technology"},{"key":"9944_CR2","unstructured":"Ahlberg, J. (2001). Candide-3\u2014an updated parameterized face. Technical report, Department of Electrical Engineering, Linkping University, Sweden"},{"issue":"1","key":"9944_CR3","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1186\/s13636-014-0036-3","volume":"2014","author":"S Ahmadi","year":"2014","unstructured":"Ahmadi, S., Ahadi, S. M., Cranen, B., & Boves, L. (2014). Sparse coding of the modulation spectrum for noise-robust automatic speech recognition. EURASIP Journal on Audio, Speech, and Music Processing, 2014(1), 36.","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"key":"9944_CR4","doi-asserted-by":"crossref","unstructured":"Amer, M. R., Siddiquie, B., Khan, S., Divakaran, A., Sawhney, H. (2014). Multimodal fusion using dynamic hybrid models. In: Proceedings of IEEE winter conference on applications of computer vision, pp 556\u2013563","DOI":"10.1109\/WACV.2014.6836053"},{"key":"9944_CR5","doi-asserted-by":"crossref","unstructured":"Benhaim, E., Sahbi, H., & Vitte, G. (2014). Continuous visual speech recognition for multimodal fusion. In: Proceedings of IEEE international conference on acoustics, speech and signal processing, pp. 4618\u20134622","DOI":"10.1109\/ICASSP.2014.6854477"},{"issue":"3","key":"9944_CR6","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1007\/s10044-002-0188-0","volume":"6","author":"JA Bilmes","year":"2003","unstructured":"Bilmes, J. A., & Kirchhoff, K. (2003). Generalized rules for combination and joint training of classifiers. Pattern Analysis and Applications, 6(3), 201\u2013211.","journal-title":"Pattern Analysis and Applications"},{"issue":"1","key":"9944_CR7","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/s10772-016-9332-x","volume":"19","author":"A Biswas","year":"2016","unstructured":"Biswas, A., Sahu, P. K., & Chandra, M. (2016). Multiple cameras audio visual speech recognition using active appearance model visual features in car environment. International Journal of Speech Technology, 19(1), 159\u2013171.","journal-title":"International Journal of Speech Technology"},{"issue":"6","key":"9944_CR8","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1109\/TSMCA.2008.2003486","volume":"38","author":"B Borgstr\u00f6m","year":"2008","unstructured":"Borgstr\u00f6m, B., & Alwan, A. (2008). A low-complexity parabolic lip contour model with speaker normalization for high-level feature extraction in noise-robust audiovisual speech recognition. IEEE Transactions on Systems, Man and Cybernetics, 38(6), 1273\u20131280.","journal-title":"IEEE Transactions on Systems, Man and Cybernetics"},{"issue":"1","key":"9944_CR9","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5\u201332.","journal-title":"Machine Learning"},{"key":"9944_CR10","unstructured":"Breslin, C. (2008). Generation and combination of complementary systems for automatic speech recognition. Ph.D. thesis, Cambridge University"},{"issue":"3","key":"9944_CR11","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1016\/j.specom.2008.09.004","volume":"51","author":"C Breslin","year":"2009","unstructured":"Breslin, C., & Gales, M. (2009). Directed decision trees for generating complementary systems. Speech Communication, 51(3), 284\u2013295.","journal-title":"Speech Communication"},{"issue":"3","key":"9944_CR12","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273\u2013297.","journal-title":"Machine Learning"},{"issue":"5","key":"9944_CR13","doi-asserted-by":"crossref","first-page":"1060","DOI":"10.1109\/TASL.2013.2244083","volume":"21","author":"L Deng","year":"2013","unstructured":"Deng, L., & Li, X. (2013). Machine learning paradigms for speech recognition: An overview. IEEE Transactions on Audio, Speech, and Language Processing, 21(5), 1060\u20131089.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9944_CR14","doi-asserted-by":"crossref","unstructured":"Dietterich, T.G. (2000). Ensemble methods in machine learning. In: Multiple classifier systems. Lecture notes in computer science (vol. 1857, pp. 1\u201315). Berlin: Springer","DOI":"10.1007\/3-540-45014-9_1"},{"issue":"5","key":"9944_CR15","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1109\/TCSVT.2004.826773","volume":"14","author":"SW Foo","year":"2004","unstructured":"Foo, S. W., Lian, Y., & Dong, L. (2004). Recognition of visual speech elements using adaptively boosted hidden Markov models. IEEE Transactions on Circuits and Systems for Video Technology, 14(5), 693\u2013705.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"5","key":"9944_CR16","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1109\/TASL.2006.878264","volume":"14","author":"MJF Gales","year":"2006","unstructured":"Gales, M. J. F., Kim, D. Y., Woodland, P. C., Chan, H. Y., Mrva, D., Sinha, R., & Tranter, S. E. (2006). Progress in the CU-HTK broadcast news transcription system. IEEE Transactions on Audio, Speech, and Language Processing, 14(5), 1513\u20131525.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9944_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-020-09717-8","author":"J Guglani","year":"2020","unstructured":"Guglani, J., & Mishra, A. N. (2020). DNN based continuous speech recognition system of Punjabi language on Kaldi toolkit. International Journal of Speech Technology. https:\/\/doi.org\/10.1007\/s10772-020-09717-8","journal-title":"International Journal of Speech Technology"},{"key":"9944_CR18","first-page":"357","volume":"4","author":"T Hain","year":"2007","unstructured":"Hain, T., Burget, L., Dines, J., Garau, G., Wan, V., Karafi, M., Vepa, J., & Lincoln, M. (2007). The AMI system for the transcription of speech in meetings. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, 4, 357\u2013360.","journal-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing"},{"key":"9944_CR19","doi-asserted-by":"crossref","unstructured":"Hu, D., Li, X., & Lu, X. (2016). Temporal multimodal learning in audiovisual speech recognition. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp. 3574\u20133582","DOI":"10.1109\/CVPR.2016.389"},{"key":"9944_CR20","first-page":"661","volume":"4","author":"R Hu","year":"2007","unstructured":"Hu, R., & Zhao, Y. (2007). A bayesian approach for phonetic decision tree state tying in conversational speech recognition. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, 4, 661\u2013664.","journal-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing"},{"key":"9944_CR21","unstructured":"Huang, F. J., & Chen, T. (1998). Advanced multimedia processing laboratory. Cornell University. Retrieved June 2020, from http:\/\/chenlab.ece.cornell.edu\/projects\/AudioVisualSpeechProcessing."},{"key":"9944_CR22","doi-asserted-by":"crossref","unstructured":"Hwang, M., Wang, W., Lei, X., Zheng, J., Cetin, O., & Peng, G. (2007). Advances in mandarin broadcast speech recognition. In: Proceedings of the 8th annual conference of the international speech communication association, pp. 2613\u20132616","DOI":"10.21437\/Interspeech.2007-589"},{"issue":"1\u20132","key":"9944_CR23","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.cviu.2006.10.019","volume":"108","author":"A Jaimes","year":"2007","unstructured":"Jaimes, A., & Sebe, N. (2007). Multimodal human-computer interaction: A survey. Computer Vision and Image Understanding, 108(1\u20132), 116\u2013134.","journal-title":"Computer Vision and Image Understanding"},{"issue":"9","key":"9944_CR24","doi-asserted-by":"crossref","first-page":"1635","DOI":"10.1109\/JPROC.2015.2459017","volume":"103","author":"AK Katsaggelos","year":"2015","unstructured":"Katsaggelos, A. K., Bahaadini, S., & Molina, R. (2015). Audiovisual fusion: Challenges and new approaches. Proceedings of the IEEE, 103(9), 1635\u20131653.","journal-title":"Proceedings of the IEEE"},{"issue":"3","key":"9944_CR25","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1109\/34.667881","volume":"20","author":"J Kittler","year":"1998","unstructured":"Kittler, J., Hatef, M., Duin, R. P. W., & Matas, J. (1998). On combining classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(3), 226\u2013239.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"4","key":"9944_CR26","doi-asserted-by":"crossref","first-page":"981","DOI":"10.1007\/s10044-017-0655-2","volume":"20","author":"M Koziarski","year":"2017","unstructured":"Koziarski, M., Krawczyk, B., & Wozniak, M. (2017). The deterministic subspace method for constructing classifier ensembles. Pattern Analysis and Applications, 20(4), 981\u2013990.","journal-title":"Pattern Analysis and Applications"},{"issue":"2","key":"9944_CR27","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1007\/s10044-015-0505-z","volume":"20","author":"B Krawczyk","year":"2017","unstructured":"Krawczyk, B., & Cyganek, B. (2017). Selecting locally specialised classifiers for one-class classification ensembles. Pattern Analysis and Applications, 20(2), 427\u2013439.","journal-title":"Pattern Analysis and Applications"},{"issue":"7","key":"9944_CR28","doi-asserted-by":"crossref","first-page":"1394","DOI":"10.1109\/TASL.2009.2015084","volume":"17","author":"N Krishnamurthy","year":"2009","unstructured":"Krishnamurthy, N., & Hansen, J. (2009). Babble noise: Modeling, analysis, and applications. IEEE Transactions on Audio, Speech, and Language Processing, 17(7), 1394\u20131407.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"1","key":"9944_CR29","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1007\/s10044-003-0199-5","volume":"7","author":"CL Liu","year":"2004","unstructured":"Liu, C. L., Hao, H., & Sako, H. (2004). Confidence transformation for combining classifiers. Pattern Analysis and Applications, 7(1), 2\u201317.","journal-title":"Pattern Analysis and Applications"},{"issue":"2","key":"9944_CR30","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1109\/34.982900","volume":"24","author":"I Matthews","year":"2002","unstructured":"Matthews, I., Cootes, T., Bangham, J. A., Cox, S., & Harvey, R. (2002). Extraction of visual features for lipreading. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(2), 198\u2013213.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"5588","key":"9944_CR31","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1038\/264746a0","volume":"264","author":"H McGurk","year":"1976","unstructured":"McGurk, H., & MacDonald, J. (1976). Hearing lips and seeing voices. Nature, 264(5588), 746\u2013748.","journal-title":"Nature"},{"issue":"2","key":"9944_CR32","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1007\/s10044-012-0313-7","volume":"17","author":"N Najkar","year":"2014","unstructured":"Najkar, N., Razzazi, F., & Sameti, H. (2014). An evolutionary decoding method for HMM-based continuous speech recognition systems using particle swarm optimization. Pattern Analysis and Applications, 17(2), 327\u2013339.","journal-title":"Pattern Analysis and Applications"},{"key":"9944_CR33","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A. (2011). Multimodal deep learning. In: Proceedings of the 28th international conference on machine learning, pp. 689\u2013696"},{"issue":"4","key":"9944_CR34","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1007\/s10489-014-0629-7","volume":"42","author":"K Noda","year":"2015","unstructured":"Noda, K., Yamaguchi, Y., Nakadai, K., Okuno, H. G., & Ogata, T. (2015). Audio-visual speech recognition using deep learning. Applied Intelligence, 42(4), 722\u2013737.","journal-title":"Applied Intelligence"},{"key":"9944_CR35","doi-asserted-by":"crossref","unstructured":"Pao, T., Liao, W., Wu, T., & Lin, C. (2009). Automatic visual feature extraction for Mandarin audio-visual speech recognition. In: Proceedings of IEEE international conference on systems, man and cybernetics, pp. 2936\u20132940","DOI":"10.1109\/ICSMC.2009.5346011"},{"issue":"3","key":"9944_CR36","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1109\/TASL.2008.2011515","volume":"17","author":"G Papandreou","year":"2009","unstructured":"Papandreou, G., Katsamanis, A., Pitsikalis, V., & Maragos, P. (2009). Adaptive multimodal fusion by uncertainty compensation with application to audiovisual speech recognition. Transactions on Audio, Speech, and Language Processing, 17(3), 423\u2013435.","journal-title":"Transactions on Audio, Speech, and Language Processing"},{"issue":"9","key":"9944_CR37","doi-asserted-by":"crossref","first-page":"1306","DOI":"10.1109\/JPROC.2003.817150","volume":"91","author":"G Potamianos","year":"2003","unstructured":"Potamianos, G., Neti, C., Gravier, G., Garg, A., & Senior, A. W. (2003). Recent advances in the automatic recognition of audio-visual speech. Proceedings of the IEEE, 91(9), 1306\u20131326.","journal-title":"Proceedings of the IEEE"},{"issue":"3","key":"9944_CR38","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1023\/A:1011352422845","volume":"4","author":"G Potamianos","year":"2001","unstructured":"Potamianos, G., Neti, C., Iyengar, G., Senior, A. W., & Verma, A. (2001). A cascade visual front end for speaker independent automatic speechreading. International Journal of Speech Technology, 4(3), 193\u2013208.","journal-title":"International Journal of Speech Technology"},{"issue":"2","key":"9944_CR39","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/s10044-013-0351-9","volume":"18","author":"OJ Prieto","year":"2015","unstructured":"Prieto, O. J., Alonso-Gonz\u00e1lez, C. J., & Rodr\u00edguez, J. J. (2015). Stacking for multivariate time series classification. Pattern Analysis and Applications, 18(2), 297\u2013312.","journal-title":"Pattern Analysis and Applications"},{"issue":"4","key":"9944_CR40","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1007\/s10772-010-9080-2","volume":"13","author":"A Puurula","year":"2010","unstructured":"Puurula, A., & Van Compernolle, D. (2010). Dual stream speech recognition using articulatory syllable models. International Journal of Speech Technology, 13(4), 219\u2013230.","journal-title":"International Journal of Speech Technology"},{"issue":"2","key":"9944_CR41","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L Rabiner","year":"1989","unstructured":"Rabiner, L. (1989). A tutorial on Hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257\u2013286.","journal-title":"Proceedings of the IEEE"},{"key":"9944_CR59","doi-asserted-by":"publisher","unstructured":"Sad G. D., Terissi L. D., G\u00f3mez J. C. (2017). Decision level fusion for audio-visual speech recognition in noisy conditions. In C. Beltr\u00e1n-Casta\u00f1\u00f3n, I. Nystr\u00f6m, F. Famili (Eds.), Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2016. Lecture Notes in Computer Science (vol. 10125). Cham: Springer. https:\/\/doi.org\/10.1007\/978-3-319-52277-7_44.","DOI":"10.1007\/978-3-319-52277-7_44"},{"issue":"1","key":"9944_CR42","doi-asserted-by":"crossref","first-page":"34","DOI":"10.3103\/S1060992X14010068","volume":"23","author":"AV Savchenko","year":"2014","unstructured":"Savchenko, A. V., & YaI, K. (2014). About neural-network algorithms application in viseme classification problem with face video in audiovisual speech recognition systems. Optical Memory and Neural Networks (information Optics), 23(1), 34\u201342.","journal-title":"Optical Memory and Neural Networks (information Optics)"},{"issue":"3","key":"9944_CR43","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1023\/A:1007614523901","volume":"37","author":"RE Schapire","year":"1999","unstructured":"Schapire, R. E., & Singer, Y. (1999). Improved boosting algorithms using confidence-rated predictions. Machine Learning, 37(3), 297\u2013336.","journal-title":"Machine Learning"},{"issue":"1","key":"9944_CR44","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1250\/ast.35.17","volume":"35","author":"P Shen","year":"2014","unstructured":"Shen, P., Tamura, S., & Hayamizu, S. (2014). Multistream sparse representation features for noise robust audio-visual speech recognition. Acoustical Science and Technology, 35(1), 17\u201327.","journal-title":"Acoustical Science and Technology"},{"issue":"3","key":"9944_CR45","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1016\/j.patcog.2010.09.011","volume":"44","author":"J Shin","year":"2011","unstructured":"Shin, J., Lee, J., & Kim, D. (2011). Real-time lip reading system for isolated Korean word recognition. Pattern Recognition, 44(3), 559\u2013571.","journal-title":"Pattern Recognition"},{"issue":"10","key":"9944_CR46","doi-asserted-by":"crossref","first-page":"1692","DOI":"10.1109\/JPROC.2010.2057231","volume":"98","author":"S Shivappa","year":"2010","unstructured":"Shivappa, S., Trivedi, M., & Rao, B. (2010). Audiovisual information fusion in human computer interfaces and intelligent environments: A survey. Proceedings of the IEEE, 98(10), 1692\u20131715.","journal-title":"Proceedings of the IEEE"},{"issue":"2","key":"9944_CR47","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1109\/TCYB.2013.2250954","volume":"44","author":"D Stewart","year":"2014","unstructured":"Stewart, D., Seymour, R., Pass, A., & Ming, J. (2014). Robust audio-visual speech recognition under noisy audio-video conditions. IEEE Transactions on Cybernetics, 44(2), 175\u2013184.","journal-title":"IEEE Transactions on Cybernetics"},{"key":"9944_CR48","doi-asserted-by":"crossref","unstructured":"St\u00fcker, S., F\u00fcgen, C., Burger, S., & W\u00f6lfel, M. (2006). Cross-system adaptation and combination for continuous speech recognition: the influence of phoneme set and acoustic front-end. In: Proceedings of the 9th international conference on spoken language processing (INTERSPEECH 2006 - ICSLP), pp. 521\u2013524","DOI":"10.21437\/Interspeech.2006-199"},{"key":"9944_CR49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2975922","author":"F Tao","year":"2020","unstructured":"Tao, F., & Busso, C. (2020). End-to-end audiovisual speech recognition system with multitask learning. IEEE Transactions on Multimedia. https:\/\/doi.org\/10.1109\/TMM.2020.2975922","journal-title":"IEEE Transactions on Multimedia"},{"issue":"6","key":"9944_CR50","first-page":"903","volume":"16","author":"LD Terissi","year":"2010","unstructured":"Terissi, L. D., & G\u00f3mez, J. C. (2010). 3D head pose and facial expression tracking using a single camera. Journal of Universal Computer Science, 16(6), 903\u2013920.","journal-title":"Journal of Universal Computer Science"},{"issue":"2","key":"9944_CR52","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1007\/s10772-018-9504-y","volume":"21","author":"LD Terissi","year":"2018","unstructured":"Terissi, L. D., Sad, G. D., & G\u00f3mez, J. C. (2018). Robust front-end for audio, visual and audio-visual speech classification. International Journal of Speech Technology, 21(2), 293\u2013307.","journal-title":"International Journal of Speech Technology"},{"key":"9944_CR51","doi-asserted-by":"crossref","unstructured":"Terissi, L. D., Sad, G. D., G\u00f3mez, J. C., & Parodi, M. (2015a). Audio-visual speech recognition scheme based on wavelets and random forests classification. In: Pardo, A., and Kittler, J. (Eds.), Progress in pattern recognition, image analysis, computer vision, and applications. CIARP 2015. Lecture notes in computer science (vol. 9423, pp. 567\u2013574). Cham: Springer","DOI":"10.1007\/978-3-319-25751-8_68"},{"key":"9944_CR58","doi-asserted-by":"publisher","unstructured":"Terissi L. D., Sad G. D., G\u00f3mez J. C., & Parodi M. (2015b). Noisy speech recognition based on combined audio-visual classifiers. In F. Schwenker, S. Scherer, L. P. Morency (Eds.), Multimodal pattern recognition of social signals in human-computer-interaction. MPRSS 2014. Lecture Notes in Computer Science (vol. 8869). Cham: Springer. https:\/\/doi.org\/10.1007\/978-3-319-14899-1_5.","DOI":"10.1007\/978-3-319-14899-1_5"},{"issue":"3","key":"9944_CR53","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1109\/TMM.2012.2233724","volume":"15","author":"F Vallet","year":"2013","unstructured":"Vallet, F., Essid, S., & Carrive, J. (2013). A multimodal approach to speaker diarization on TV talk-shows. IEEE Transactions on Multimedia, 15(3), 509\u2013520.","journal-title":"IEEE Transactions on Multimedia"},{"issue":"3","key":"9944_CR54","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"Varga, A., & Steeneken, H. J. M. (1993). Assessment for automatic speech recognition II: NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems. Speech Communication, 12(3), 247\u2013251.","journal-title":"Speech Communication"},{"key":"9944_CR55","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.specom.2013.09.008","volume":"57","author":"P Wagner","year":"2014","unstructured":"Wagner, P., Malisz, Z., & Kopp, S. (2014). Gesture and speech in interaction: An overview. Speech Communication, 57, 209\u2013232.","journal-title":"Speech Communication"},{"key":"9944_CR56","doi-asserted-by":"crossref","unstructured":"Zeiler, S., Nicheli, R., Ma, N., Brown, G. J., & Kolossa, D. (2016). Robust audiovisual speech recognition using noise-adaptive linear discriminant analysis. In: Proceedings of IEEE international conference on acoustics, speech and signal processing, pp. 2797\u20132801","DOI":"10.1109\/ICASSP.2016.7472187"},{"issue":"7","key":"9944_CR57","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/TMM.2009.2030637","volume":"11","author":"G Zhao","year":"2009","unstructured":"Zhao, G., Barnard, M., & Pietik\u00e4inen, M. (2009). Lipreading with local spatiotemporal descriptors. IEEE Transactions on Multimedia, 11(7), 1254\u20131265.","journal-title":"IEEE Transactions on Multimedia"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09944-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-021-09944-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09944-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T18:39:22Z","timestamp":1647369562000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-021-09944-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,7]]},"references-count":59,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["9944"],"URL":"https:\/\/doi.org\/10.1007\/s10772-021-09944-7","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2022,1,7]]},"assertion":[{"value":"10 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}