{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:30:31Z","timestamp":1743075031310,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":15,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819967018"},{"type":"electronic","value":"9789819967025"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-981-99-6702-5_16","type":"book-chapter","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:02:42Z","timestamp":1700503362000},"page":"197-208","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-Modal Knowledge Distillation for\u00a0Audiovisual Speech Recognition"],"prefix":"10.1007","author":[{"given":"L.","family":"Ashok Kumar","sequence":"first","affiliation":[]},{"given":"D.","family":"Karthika Renuka","sequence":"additional","affiliation":[]},{"given":"V.","family":"Dineshraja","sequence":"additional","affiliation":[]},{"given":"Fatima","family":"Abdul Jabbar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,21]]},"reference":[{"key":"16_CR1","unstructured":"Torfi, A, Shirvani, R.A, Keneshloo, Y, Tavaf, N, Fox, E.A.: Natural language processing advancements by deep learning: a survey (2020). arXiv preprint arXiv:2003.01200"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Nefian, A.V, Liang, L., Pi, X., Xiaoxiang, L., Mao, C., Murphy, K.: A coupled HMM for audio-visual speech recognition. In: 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 2, pp. II-2013. IEEE (2002)","DOI":"10.1109\/ICASSP.2002.1006167"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Baevski, A., Mohamed, A.: Effectiveness of self-supervised pre-training for asr. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7694\u20137698. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054224"},{"key":"16_CR4","unstructured":"Neti, C., Potamianos, G., Luettin, J., Matthews, I., Glotin, H., Vergyri, D., Mashari, A.: Audio visual speech recognition (2000)"},{"key":"16_CR5","unstructured":"Xiao, F., Lee, Y.J., Grauman, K., Malik, J., Feichtenhofer, C.: Audiovisual slowfast networks for video recognition (2020). arXiv preprint arXiv:2001.08740"},{"issue":"9","key":"16_CR6","doi-asserted-by":"publisher","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.: Recent advances in the automatic recognition of audiovisual speech. Proc. IEEE 91(9), 1306\u20131326 (2003)","journal-title":"Proc. IEEE"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Guo, P., Chang, X., Watanabe, S., Xie, L.: Multi-speaker ASR combining non-autoregressive conformer CTC and conditional speaker chain (2021). arXiv preprint arXiv:2106.08595","DOI":"10.21437\/Interspeech.2021-2155"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Huang, W.C., Wu, C.H., Luo, S.B., Chen, K.Y., Wang, H.M., Toda, T.: Speech recognition by simply fine-tuning BERT. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7343\u20137347. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413668"},{"issue":"6","key":"16_CR9","doi-asserted-by":"publisher","first-page":"172988142097608","DOI":"10.1177\/1729881420976082","volume":"17","author":"L Xia","year":"2020","unstructured":"Xia, L., Chen, G., Xu, X., Cui, J., Gao, Y.: Audiovisual speech recognition: a review and forecast. Int. J. Adv. Robot. Syst. 17(6), 1729881420976082 (2020)","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Sheshadri, A.K., Vijjini, A.R., Kharbanda, S.: WER-BERT: automatic WER estimation with BERT in a balanced ordinal classification paradigm (2021). arXiv preprint arXiv:2101.05478","DOI":"10.18653\/v1\/2021.eacl-main.320"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Yu, J., Zhang, S.X., Wu, J., Ghorbani, S., Wu, B., Kang, S., Yu, D.: Audio-visual recognition of overlapped speech for the lrs2 dataset. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6984\u20136988. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054127"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Petridis, S., Stafylakis, T., Ma, P., Tzimiropoulos, G., Pantic, M.: Audio-visual speech recognition with a hybrid CTC\/attention architecture. In: 2018 IEEE Spoken Language Technology Workshop (SLT), pp. 513\u2013520. IEEE","DOI":"10.1109\/SLT.2018.8639643"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Makino, T., Liao, H., Assael, Y., Shillingford, B., Garcia, B., Braga, O., Siohan, O.: Recurrent neural network transducer for audio-visual speech recognition. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 905\u2013912. IEEE (2019)","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"16_CR14","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 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 2143\u20132147). IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"16_CR15","unstructured":"Yu, F.H., Chen, K.Y.: Non-autoregressive transformer-based end-to-end ASR using BERT (2021). arXiv preprint arXiv:2104.04805"}],"container-title":["Smart Innovation, Systems and Technologies","Evolution in Computational Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-6702-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T06:07:32Z","timestamp":1728454052000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-6702-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819967018","9789819967025"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-6702-5_16","relation":{},"ISSN":["2190-3018","2190-3026"],"issn-type":[{"type":"print","value":"2190-3018"},{"type":"electronic","value":"2190-3026"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"21 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"FICTA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Frontiers of Intelligent Computing: Theory and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cardiff","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 April 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 April 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ficta2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ficta.co.uk\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}