{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T12:52:54Z","timestamp":1743079974018,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819611508"},{"type":"electronic","value":"9789819611515"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-1151-5_14","type":"book-chapter","created":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T16:01:11Z","timestamp":1738857671000},"page":"136-145","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cued Speech-Integrated Audio-Visual Variational Autoencoder for\u00a0Speech Enhancement"],"prefix":"10.1007","author":[{"given":"Lufei","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Rong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,7]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Afouras, T., Chung, J.S., Zisserman, A.: The conversation: deep audio-visual speech enhancement. arXiv preprint arXiv:1804.04121 (2018)","key":"14_CR1","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"14_CR2","doi-asserted-by":"publisher","first-page":"2993","DOI":"10.1109\/TASLP.2022.3207349","volume":"30","author":"X Bie","year":"2022","unstructured":"Bie, X., Leglaive, S., Alameda-Pineda, X., Girin, L.: Unsupervised speech enhancement using dynamical variational autoencoders. IEEE\/ACM Trans. Audio Speech Lang. Process. 30, 2993\u20133007 (2022)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"1","key":"14_CR3","first-page":"3","volume":"112","author":"RO Cornett","year":"1967","unstructured":"Cornett, R.O.: Cued speech. Am. Ann. Deaf 112(1), 3\u201313 (1967)","journal-title":"Am. Ann. Deaf"},{"issue":"4","key":"14_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3197517.3201357","volume":"37","author":"A Ephrat","year":"2018","unstructured":"Ephrat, A., et al.: Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation. ACM Trans. Graph. (TOG) 37(4), 1\u201311 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"3","key":"14_CR5","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1162\/neco.2008.04-08-771","volume":"21","author":"C F\u00e9votte","year":"2009","unstructured":"F\u00e9votte, C., Bertin, N., Durrieu, J.L.: Nonnegative matrix factorization with the Itakura-Saito divergence: with application to music analysis. Neural Comput. 21(3), 793\u2013830 (2009)","journal-title":"Neural Comput."},{"doi-asserted-by":"crossref","unstructured":"Gao, L., Huang, S., Liu, L.: A novel interpretable and generalizable re-synchronization model for cued speech based on a multi-cuer corpus. arXiv preprint arXiv:2306.02596 (2023)","key":"14_CR6","DOI":"10.21437\/Interspeech.2023-663"},{"doi-asserted-by":"crossref","unstructured":"Girin, L., Leglaive, S., Bie, X., Diard, J., Hueber, T., Alameda-Pineda, X.: Dynamical variational autoencoders: a comprehensive review. arXiv preprint arXiv:2008.12595 (2020)","key":"14_CR7","DOI":"10.1561\/9781680839135"},{"unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)","key":"14_CR8"},{"doi-asserted-by":"crossref","unstructured":"Leglaive, S., Alameda-Pineda, X., Girin, L., Horaud, R.: A recurrent variational autoencoder for speech enhancement. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 371\u2013375. IEEE (2020)","key":"14_CR9","DOI":"10.1109\/ICASSP40776.2020.9053164"},{"doi-asserted-by":"crossref","unstructured":"Lei, W., Liu, L., Wang, J.: Bridge to non-barrier communication: Gloss-prompted fine-grained cued speech gesture generation with diffusion model. arXiv preprint arXiv:2404.19277 (2024)","key":"14_CR10","DOI":"10.24963\/ijcai.2024\/700"},{"doi-asserted-by":"crossref","unstructured":"Liu, L., Liu, L.: Cross-modal mutual learning for cued speech recognition. In: Proceedings of IEEE-ICASSP, pp.\u00a01\u20135 (2023)","key":"14_CR11","DOI":"10.1109\/ICASSP49357.2023.10095271"},{"doi-asserted-by":"crossref","unstructured":"Liu, L., Liu, L., Li, H.: Computation and parameter efficient multi-modal fusion transformer for cued speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. (2024)","key":"14_CR12","DOI":"10.1109\/TASLP.2024.3363446"},{"issue":"4","key":"14_CR13","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1353\/aad.2019.0031","volume":"164","author":"L Liu","year":"2019","unstructured":"Liu, L., Feng, G.: A pilot study on mandarin Chinese cued speech. Am. Ann. Deaf 164(4), 496\u2013518 (2019)","journal-title":"Am. Ann. Deaf"},{"key":"14_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13640-017-0233-y","volume":"2017","author":"L Liu","year":"2017","unstructured":"Liu, L., Feng, G., Beautemps, D.: Inner lips feature extraction based on CLNF with hybrid dynamic template for cued speech. EURASIP J. Image Video Process. 2017, 1\u201315 (2017)","journal-title":"EURASIP J. Image Video Process."},{"doi-asserted-by":"crossref","unstructured":"Liu, L., Feng, G., Beautemps, D., Zhang, X.P.: A novel resynchronization procedure for hand-lips fusion applied to continuous French cued speech recognition. In: 2019 27th European Signal Processing Conference (EUSIPCO), pp.\u00a01\u20135. IEEE (2019)","key":"14_CR15","DOI":"10.23919\/EUSIPCO.2019.8903053"},{"key":"14_CR16","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1109\/TMM.2020.2976493","volume":"23","author":"L Liu","year":"2020","unstructured":"Liu, L., Feng, G., Denis, B., Zhang, X.P.: Re-synchronization using the hand preceding model for multi-modal fusion in automatic continuous cued speech recognition. IEEE Trans. Multimedia 23, 292\u2013305 (2020)","journal-title":"IEEE Trans. Multimedia"},{"doi-asserted-by":"crossref","unstructured":"Liu, L., Feng, G., Ren, X., Ma, X.: Objective hand complexity comparison between two mandarin Chinese cued speech systems. In: Proceedings of IEEE-ISCSLP, pp. 215\u2013219 (2022)","key":"14_CR17","DOI":"10.1109\/ISCSLP57327.2022.10037814"},{"key":"14_CR18","doi-asserted-by":"publisher","first-page":"1368","DOI":"10.1109\/TASLP.2021.3066303","volume":"29","author":"D Michelsanti","year":"2021","unstructured":"Michelsanti, D., et al.: An overview of deep-learning-based audio-visual speech enhancement and separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 1368\u20131396 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"doi-asserted-by":"crossref","unstructured":"Sadeghi, M., Alameda-Pineda, X.: Robust unsupervised audio-visual speech enhancement using a mixture of variational autoencoders. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7534\u20137538. IEEE (2020)","key":"14_CR19","DOI":"10.1109\/ICASSP40776.2020.9053730"},{"key":"14_CR20","doi-asserted-by":"publisher","first-page":"1899","DOI":"10.1109\/TSP.2021.3066038","volume":"69","author":"M Sadeghi","year":"2021","unstructured":"Sadeghi, M., Alameda-Pineda, X.: Mixture of inference networks for VAE-based audio-visual speech enhancement. IEEE Trans. Signal Process. 69, 1899\u20131909 (2021)","journal-title":"IEEE Trans. Signal Process."},{"doi-asserted-by":"crossref","unstructured":"Sadeghi, M., Alameda-Pineda, X.: Switching variational auto-encoders for noise-agnostic audio-visual speech enhancement. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6663\u20136667. IEEE (2021)","key":"14_CR21","DOI":"10.1109\/ICASSP39728.2021.9414097"},{"key":"14_CR22","doi-asserted-by":"publisher","first-page":"1788","DOI":"10.1109\/TASLP.2020.3000593","volume":"28","author":"M Sadeghi","year":"2020","unstructured":"Sadeghi, M., Leglaive, S., Alameda-Pineda, X., Girin, L., Horaud, R.: Audio-visual speech enhancement using conditional variational auto-encoders. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 1788\u20131800 (2020)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"doi-asserted-by":"crossref","unstructured":"Sadeghi, M., Serizel, R.: Fast and efficient speech enhancement with variational autoencoders. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","key":"14_CR23","DOI":"10.1109\/ICASSP49357.2023.10095237"},{"issue":"4","key":"14_CR24","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1093\/deafed\/enx026","volume":"22","author":"BJ Trezek","year":"2017","unstructured":"Trezek, B.J.: Cued speech and the development of reading in english: examining the evidence. J. Deaf Stud. Deaf Educ. 22(4), 349\u2013364 (2017)","journal-title":"J. Deaf Stud. Deaf Educ."},{"doi-asserted-by":"crossref","unstructured":"Wang, J., Tang, Z., Li, X., Yu, M., Fang, Q., Liu, L.: Cross-modal knowledge distillation method for automatic cued speech recognition (2021)","key":"14_CR25","DOI":"10.21437\/Interspeech.2021-432"},{"doi-asserted-by":"crossref","unstructured":"Zhang, Y., Liu, L., Liu, L.: Cuing without sharing: a federated cued speech recognition framework via mutual knowledge distillation. arXiv preprint arXiv:2308.03432 (2023)","key":"14_CR26","DOI":"10.1145\/3581783.3612134"}],"container-title":["Lecture Notes in Computer Science","Social Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-1151-5_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T16:01:20Z","timestamp":1738857680000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1151-5_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819611508","9789819611515"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1151-5_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"7 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICSR + InnoBiz","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Social Robotics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"socrob2024b","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.asianlp.sg\/conferences\/icsr2024\/web\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}