{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:19:23Z","timestamp":1782404363053,"version":"3.54.5"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200588","type":"print"},{"value":"9783031200595","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20059-5_33","type":"book-chapter","created":{"date-parts":[[2022,10,28]],"date-time":"2022-10-28T16:02:50Z","timestamp":1666972970000},"page":"576-593","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Speaker-Adaptive Lip Reading with User-Dependent Padding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6514-0018","authenticated-orcid":false,"given":"Minsu","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6524-8689","authenticated-orcid":false,"given":"Hyunjun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5306-6853","authenticated-orcid":false,"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,29]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Abdel-Hamid, O., Jiang, H.: Fast speaker adaptation of hybrid NN\/HMM model for speech recognition based on discriminative learning of speaker code. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 7942\u20137946. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639211"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Abdel-Hamid, O., Jiang, H.: Rapid and effective speaker adaptation of convolutional neural network based models for speech recognition. In: INTERSPEECH, pp. 1248\u20131252 (2013)","DOI":"10.21437\/Interspeech.2013-336"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Afouras, T., Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Deep audio-visual speech recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2018)","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"33_CR4","unstructured":"Afouras, T., Chung, J.S., Zisserman, A.: LRS3-TED: a large-scale dataset for visual speech recognition. arXiv preprint arXiv:1809.00496 (2018)"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Afouras, T., Chung, J.S., Zisserman, A.: ASR is all you need: cross-modal distillation for lip reading. In: ICASSP 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2143\u20132147. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Almajai, I., Cox, S., Harvey, R., Lan, Y.: Improved speaker independent lip reading using speaker adaptive training and deep neural networks. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2722\u20132726. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472172"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Anastasakos, T., McDonough, J., Makhoul, J.: Speaker adaptive training: a maximum likelihood approach to speaker normalization. In: 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 2, pp. 1043\u20131046. IEEE (1997)","DOI":"10.1109\/ICASSP.1997.596119"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Anvari, Z., Athitsos, V.: A pipeline for automated face dataset creation from unlabeled images. In: Proceedings of the 12th ACM International Conference on PErvasive Technologies Related to Assistive Environments, pp. 227\u2013235 (2019)","DOI":"10.1145\/3316782.3321522"},{"key":"33_CR9","unstructured":"Assael, Y.M., Shillingford, B., Whiteson, S., De Freitas, N.: LipNet: end-to-end sentence-level lipreading. arXiv preprint arXiv:1611.01599 (2016)"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Lip reading sentences in the wild. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3444\u20133453. IEEE (2017)","DOI":"10.1109\/CVPR.2017.367"},{"key":"33_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-54184-6_6","volume-title":"Computer Vision \u2013 ACCV 2016","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10112, pp. 87\u2013103. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54184-6_6"},{"key":"33_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-319-54427-4_19","volume-title":"Computer Vision \u2013 ACCV 2016 Workshops","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Chen, C.-S., Lu, J., Ma, K.-K. (eds.) ACCV 2016. LNCS, vol. 10117, pp. 251\u2013263. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54427-4_19"},{"issue":"5","key":"33_CR13","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.: An audio-visual corpus for speech perception and automatic speech recognition. J. Acoust. Soc. Am. 120(5), 2421\u20132424 (2006)","journal-title":"J. Acoust. Soc. Am."},{"issue":"4","key":"33_CR14","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2010","unstructured":"Dehak, N., Kenny, P.J., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788\u2013798 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Ververas, E., Kotsia, I., Zafeiriou, S.: RetinaFace: single-shot multi-level face localisation in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5203\u20135212 (2020)","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"issue":"5","key":"33_CR17","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/89.466659","volume":"3","author":"VV Digalakis","year":"1995","unstructured":"Digalakis, V.V., Rtischev, D., Neumeyer, L.G.: Speaker adaptation using constrained estimation of Gaussian mixtures. IEEE Trans. Speech Audio Process. 3(5), 357\u2013366 (1995)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"33_CR18","unstructured":"Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: International Conference on Machine Learning, pp. 1180\u20131189. PMLR (2015)"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Gopinath, R.A.: Maximum likelihood modeling with gaussian distributions for classification. In: Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998 (Cat. No. 98CH36181), vol. 2, pp. 661\u2013664. IEEE (1998)","DOI":"10.1109\/ICASSP.1998.675351"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"33_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-46487-9_6","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Y Guo","year":"2016","unstructured":"Guo, Y., Zhang, L., Hu, Y., He, X., Gao, J.: MS-Celeb-1M: a dataset and benchmark for large-scale face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 87\u2013102. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_6"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"33_CR23","doi-asserted-by":"publisher","first-page":"3654","DOI":"10.1109\/TASLP.2021.3126925","volume":"29","author":"J Hong","year":"2021","unstructured":"Hong, J., Kim, M., Park, S.J., Ro, Y.M.: Speech reconstruction with reminiscent sound via visual voice memory. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 3654\u20133667 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Huang, Y., He, L., Wei, W., Gale, W., Li, J., Gong, Y.: Using personalized speech synthesis and neural language generator for rapid speaker adaptation. In: ICASSP 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7399\u20137403. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053104"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Kandala, P.A., et al.: Speaker adaptation for lip-reading using visual identity vectors. In: INTERSPEECH, pp. 2758\u20132762 (2019)","DOI":"10.21437\/Interspeech.2019-3237"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Kim, M., Hong, J., Park, S.J., Ro, Y.M.: CroMM-VSR: cross-modal memory augmented visual speech recognition. IEEE Trans. Multimedia (2021)","DOI":"10.1109\/TMM.2021.3115626"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Kim, M., Hong, J., Park, S.J., Ro, Y.M.: Multi-modality associative bridging through memory: speech sound recollected from face video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 296\u2013306 (2021)","DOI":"10.1109\/ICCV48922.2021.00036"},{"key":"33_CR28","first-page":"2758","volume":"34","author":"M Kim","year":"2021","unstructured":"Kim, M., Hong, J., Ro, Y.M.: Lip to speech synthesis with visual context attentional GAN. Adv. Neural. Inf. Process. Syst. 34, 2758\u20132770 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Kim, M., Yeo, J.H., Ro, Y.M.: Distinguishing homophenes using multi-head visual-audio memory for lip reading. In: Proceedings of the 36th AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada, vol. 22 (2022)","DOI":"10.1609\/aaai.v36i1.20003"},{"key":"33_CR30","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"33_CR31","doi-asserted-by":"crossref","unstructured":"Klejch, O., Fainberg, J., Bell, P., Renals, S.: Speaker adaptive training using model agnostic meta-learning. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 881\u2013888. IEEE (2019)","DOI":"10.1109\/ASRU46091.2019.9003751"},{"key":"33_CR32","unstructured":"Lee, D.H., et al.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, ICML, vol. 3, p. 896 (2013)"},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Li, B., Sim, K.C.: Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN\/HMM systems. In: Eleventh Annual Conference of the International Speech Communication Association (2010)","DOI":"10.21437\/Interspeech.2010-214"},{"key":"33_CR34","unstructured":"Li, X., Bilmes, J.: Regularized adaptation of discriminative classifiers. In: 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, vol. 1, pp. I. IEEE (2006)"},{"key":"33_CR35","doi-asserted-by":"crossref","unstructured":"Liao, H., McDermott, E., Senior, A.: Large scale deep neural network acoustic modeling with semi-supervised training data for YouTube video transcription. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 368\u2013373. IEEE (2013)","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"33_CR36","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Ma, P., Mira, R., Petridis, S., Schuller, B.W., Pantic, M.: LiRA: learning visual speech representations from audio through self-supervision. arXiv preprint arXiv:2106.09171 (2021)","DOI":"10.21437\/Interspeech.2021-1360"},{"key":"33_CR38","doi-asserted-by":"crossref","unstructured":"Martinez, B., Ma, P., Petridis, S., Pantic, M.: Lipreading using temporal convolutional networks. In: ICASSP 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6319\u20136323. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"33_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/978-3-030-58574-7_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Mei","year":"2020","unstructured":"Mei, K., Zhu, C., Zou, J., Zhang, S.: Instance adaptive self-training for unsupervised domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 415\u2013430. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58574-7_25"},{"key":"33_CR40","doi-asserted-by":"crossref","unstructured":"Meng, Z., et al.: Speaker-invariant training via adversarial learning. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5969\u20135973. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461932"},{"key":"33_CR41","doi-asserted-by":"crossref","unstructured":"Miao, Y., Zhang, H., Metze, F.: Towards speaker adaptive training of deep neural network acoustic models. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)","DOI":"10.21437\/Interspeech.2014-490"},{"issue":"11","key":"33_CR42","doi-asserted-by":"publisher","first-page":"1938","DOI":"10.1109\/TASLP.2015.2457612","volume":"23","author":"Y Miao","year":"2015","unstructured":"Miao, Y., Zhang, H., Metze, F.: Speaker adaptive training of deep neural network acoustic models using i-vectors. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(11), 1938\u20131949 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"33_CR43","unstructured":"Mira, R., Haliassos, A., Petridis, S., Schuller, B.W., Pantic, M.: SVTS: scalable video-to-speech synthesis. arXiv preprint arXiv:2205.02058 (2022)"},{"key":"33_CR44","doi-asserted-by":"crossref","unstructured":"Mira, R., Vougioukas, K., Ma, P., Petridis, S., Schuller, B.W., Pantic, M.: End-to-end video-to-speech synthesis using generative adversarial networks. IEEE Trans. Cybern. (2022)","DOI":"10.1109\/TCYB.2022.3162495"},{"key":"33_CR45","doi-asserted-by":"crossref","unstructured":"Neto, J., et al.: Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system (1995)","DOI":"10.21437\/Eurospeech.1995-411"},{"key":"33_CR46","doi-asserted-by":"crossref","unstructured":"Noda, K., Yamaguchi, Y., Nakadai, K., Okuno, H.G., Ogata, T.: Lipreading using convolutional neural network. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)","DOI":"10.21437\/Interspeech.2014-293"},{"key":"33_CR47","doi-asserted-by":"crossref","unstructured":"Petridis, S., Stafylakis, T., Ma, P., Cai, F., Tzimiropoulos, G., Pantic, M.: End-to-end audiovisual speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6548\u20136552. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"33_CR48","doi-asserted-by":"crossref","unstructured":"Ren, S., Du, Y., Lv, J., Han, G., He, S.: Learning from the master: distilling cross-modal advanced knowledge for lip reading. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13325\u201313333 (2021)","DOI":"10.1109\/CVPR46437.2021.01312"},{"key":"33_CR49","doi-asserted-by":"crossref","unstructured":"Seide, F., Li, G., Chen, X., Yu, D.: Feature engineering in context-dependent deep neural networks for conversational speech transcription. In: 2011 IEEE Workshop on Automatic Speech Recognition & Understanding, pp. 24\u201329. IEEE (2011)","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"33_CR50","doi-asserted-by":"crossref","unstructured":"Stafylakis, T., Tzimiropoulos, G.: Combining residual networks with LSTMs for lipreading. arXiv preprint arXiv:1703.04105 (2017)","DOI":"10.21437\/Interspeech.2017-85"},{"key":"33_CR51","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"33_CR52","doi-asserted-by":"crossref","unstructured":"Swietojanski, P., Renals, S.: Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models. In: 2014 IEEE Spoken Language Technology Workshop (SLT), pp. 171\u2013176. IEEE (2014)","DOI":"10.1109\/SLT.2014.7078569"},{"key":"33_CR53","doi-asserted-by":"crossref","unstructured":"Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7167\u20137176 (2017)","DOI":"10.1109\/CVPR.2017.316"},{"key":"33_CR54","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"33_CR55","doi-asserted-by":"crossref","unstructured":"Vesel\u1ef3, K., Hannemann, M., Burget, L.: Semi-supervised training of deep neural networks. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 267\u2013272. IEEE (2013)","DOI":"10.1109\/ASRU.2013.6707741"},{"key":"33_CR56","unstructured":"Weng, X., Kitani, K.: Learning spatio-temporal features with two-stream deep 3D CNNs for lipreading. arXiv preprint arXiv:1905.02540 (2019)"},{"key":"33_CR57","doi-asserted-by":"crossref","unstructured":"Xiao, J., Yang, S., Zhang, Y., Shan, S., Chen, X.: Deformation flow based two-stream network for lip reading. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), pp. 364\u2013370. IEEE (2020)","DOI":"10.1109\/FG47880.2020.00132"},{"key":"33_CR58","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M.T., Hovy, E., Le, Q.V.: Self-training with noisy student improves ImageNet classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10687\u201310698 (2020)","DOI":"10.1109\/CVPR42600.2020.01070"},{"issue":"12","key":"33_CR59","doi-asserted-by":"publisher","first-page":"1713","DOI":"10.1109\/TASLP.2014.2346313","volume":"22","author":"S Xue","year":"2014","unstructured":"Xue, S., Abdel-Hamid, O., Jiang, H., Dai, L., Liu, Q.: Fast adaptation of deep neural network based on discriminant codes for speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 22(12), 1713\u20131725 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"33_CR60","doi-asserted-by":"crossref","unstructured":"Yang, C., Wang, S., Zhang, X., Zhu, Y.: Speaker-independent lipreading with limited data. In: 2020 IEEE International Conference on Image Processing (ICIP), pp. 2181\u20132185. IEEE (2020)","DOI":"10.1109\/ICIP40778.2020.9190780"},{"key":"33_CR61","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: LRW-1000: a naturally-distributed large-scale benchmark for lip reading in the wild. In: 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), pp. 1\u20138. IEEE (2019)","DOI":"10.1109\/FG.2019.8756582"},{"key":"33_CR62","doi-asserted-by":"crossref","unstructured":"Yarowsky, D.: Unsupervised word sense disambiguation rivaling supervised methods. In: 33rd Annual Meeting of the Association for Computational Linguistics, pp. 189\u2013196 (1995)","DOI":"10.3115\/981658.981684"},{"key":"33_CR63","doi-asserted-by":"crossref","unstructured":"Yu, D., Yao, K., Su, H., Li, G., Seide, F.: KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 7893\u20137897. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"33_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Wang, S., Chen, G.: Speaker-independent lipreading by disentangled representation learning. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 2493\u20132497. IEEE (2021)","DOI":"10.1109\/ICIP42928.2021.9506396"},{"issue":"7","key":"33_CR65","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/TMM.2009.2030637","volume":"11","author":"G Zhao","year":"2009","unstructured":"Zhao, G., Barnard, M., Pietikainen, M.: Lipreading with local spatiotemporal descriptors. IEEE Trans. Multimedia 11(7), 1254\u20131265 (2009)","journal-title":"IEEE Trans. Multimedia"},{"key":"33_CR66","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xu, R., Wang, X., Hou, P., Tang, H., Song, M.: Hearing lips: improving lip reading by distilling speech recognizers. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 6917\u20136924 (2020)","DOI":"10.1609\/aaai.v34i04.6174"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20059-5_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T20:00:09Z","timestamp":1728244809000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20059-5_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200588","9783031200595"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20059-5_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"29 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}