{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T05:08:45Z","timestamp":1748668125201,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030878016"},{"type":"electronic","value":"9783030878023"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-87802-3_4","type":"book-chapter","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T23:36:52Z","timestamp":1632267412000},"page":"36-49","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Designing and Deploying an Interaction Modality for Articulatory-Based Audiovisual Speech Synthesis"],"prefix":"10.1007","author":[{"given":"Nuno","family":"Almeida","sequence":"first","affiliation":[]},{"given":"Diogo","family":"Cunha","sequence":"additional","affiliation":[]},{"given":"Samuel","family":"Silva","sequence":"additional","affiliation":[]},{"given":"Ant\u00f3nio","family":"Teixeira","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,22]]},"reference":[{"key":"4_CR1","doi-asserted-by":"publisher","first-page":"11","DOI":"10.3390\/s19112587","volume":"19","author":"N Almeida","year":"2019","unstructured":"Almeida, N., Teixeira, A., Silva, S., Ketsmur, M.: The AM4I architecture and framework for multimodal interaction and its application to smart environments. Sensors 19, 11 (2019). https:\/\/doi.org\/10.3390\/s19112587. Switzerland","journal-title":"Sensors"},{"key":"4_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1007\/978-3-319-07230-2_36","volume-title":"Human-Computer Interaction. Advanced Interaction Modalities and Techniques","author":"N Almeida","year":"2014","unstructured":"Almeida, N., Silva, S., Teixeira, A.: Design and development of speech interaction: a methodology. In: Kurosu, M. (ed.) HCI 2014, Part II. LNCS, vol. 8511, pp. 370\u2013381. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-07230-2_36"},{"issue":"3","key":"4_CR3","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s12193-013-0120-5","volume":"7","author":"DA Dahl","year":"2013","unstructured":"Dahl, D.A.: The W3C multimodal architecture and interfaces standard. J. Multimodal User Interfaces 7(3), 171\u2013182 (2013). https:\/\/doi.org\/10.1007\/s12193-013-0120-5","journal-title":"J. Multimodal User Interfaces"},{"key":"4_CR4","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.specom.2017.08.011","volume":"95","author":"PP Filntisis","year":"2017","unstructured":"Filntisis, P.P., Katsamanis, A., Tsiakoulis, P., Maragos, P.: Video-realistic expressive audio-visual speech synthesis for the Greek language. Speech Commun. 95, 137\u2013152 (2017)","journal-title":"Speech Commun."},{"key":"4_CR5","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.specom.2014.11.001","volume":"66","author":"W Mattheyses","year":"2015","unstructured":"Mattheyses, W., Verhelst, W.: Audiovisual speech synthesis: an overview of the state-of-the-art. Speech Commun. 66, 182\u2013217 (2015). https:\/\/doi.org\/10.1016\/j.specom.2014.11.001","journal-title":"Speech Commun."},{"key":"4_CR6","unstructured":"Nam, H., Goldstein, L., Browman, C., Rubin, P., Proctor, M., Saltzman, E.: Tada (task dynamics application) manual (2006)"},{"key":"4_CR7","unstructured":"Oliveira, C.A.M.D.: Do grafema ao gesto: contributos lingu\u00edsticos para um sistema de s\u00edntese de base articulat\u00f3ria. Ph.D. thesis, Universidade de Aveiro (2009). https:\/\/ria.ua.pt\/handle\/10773\/4847"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Prenger, R., Valle, R., Catanzaro, B.: WaveGlow: a flow-based generative network for speech synthesis. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019, pp. 3617\u20133621. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"4_CR9","doi-asserted-by":"publisher","unstructured":"Rao, K., Peng, F., Sak, H., Beaufays, F.: Grapheme-to-phoneme conversion using Long Short-Term Memory recurrent neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4225\u20134229 (2015). https:\/\/doi.org\/10.1109\/ICASSP.2015.7178767","DOI":"10.1109\/ICASSP.2015.7178767"},{"key":"4_CR10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-42816-1_15","volume-title":"Multimodal Interaction with W3C Standards","author":"BH Rodr\u00edguez","year":"2017","unstructured":"Rodr\u00edguez, B.H., Moissinac, J.C.: Discovery and registration: finding and integrating components into dynamic systems. In: Dahl, D. (ed.) Multimodal Interaction with W3C Standards. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-42816-1_15"},{"issue":"2","key":"4_CR11","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1121\/1.386780","volume":"70","author":"P Rubin","year":"1981","unstructured":"Rubin, P., Baer, T., Mermelstein, P.: An articulatory synthesizer for perceptual research. J. Acoust. Soc. Am. 70(2), 321\u2013328 (1981)","journal-title":"J. Acoust. Soc. Am."},{"issue":"4","key":"4_CR12","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1207\/s15326969eco0104_2","volume":"1","author":"EL Saltzman","year":"1989","unstructured":"Saltzman, E.L., Munhall, K.G.: A dynamical approach to gestural patterning in speech production. Ecol. Psychol. 1(4), 333\u2013382 (1989)","journal-title":"Ecol. Psychol."},{"key":"4_CR13","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/978-3-642-35292-8_28","volume-title":"Advances in Speech and Language Technologies for Iberian Languages","author":"J Serra","year":"2012","unstructured":"Serra, J., Ribeiro, M., Freitas, J., Orvalho, V., Dias, M.S.: A proposal for a visual speech animation system for European Portuguese. In: Torre Toledano, D., et al. (eds.) IberSPEECH 2012. CCIS, vol. 328, pp. 267\u2013276. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-35292-8_28"},{"key":"4_CR14","unstructured":"Silva, S., Teixeira, A., Orvalho, V.: Articulatory-based audiovisual speech synthesis: proof of concept for European Portuguese. In: Proceedings of the Iberspeech, Lisbon, Portugal, pp. 119\u2013126 (2016)"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Silva, S., Teixeira, A.J.S.: An anthropomorphic perspective for audiovisual speech synthesis. In: BIOSIGNALS, pp. 163\u2013172 (2017)","DOI":"10.5220\/0006150201630172"},{"issue":"4","key":"4_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073640","volume":"36","author":"S Suwajanakorn","year":"2017","unstructured":"Suwajanakorn, S., Seitz, S.M., Kemelmacher-Shlizerman, I.: Synthesizing Obama: learning lip sync from audio. ACM Trans. Graph. (ToG) 36(4), 1\u201313 (2017)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"4_CR17","doi-asserted-by":"publisher","unstructured":"Teixeira, A., Silva, L., Martinez, R., Vaz, F.: Sapwindows - towards a versatile modular articulatory synthesizer. In: Proceedings of 2002 IEEE Workshop on Speech Synthesis, pp. 31\u201334 (2002). https:\/\/doi.org\/10.1109\/WSS.2002.1224366","DOI":"10.1109\/WSS.2002.1224366"},{"key":"4_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-42816-1_12","volume-title":"Multimodal Interaction with W3C Standards.","author":"A Teixeira","year":"2017","unstructured":"Teixeira, A., Almeida, N., Pereira, C., Oliveira e Silva, M., Vieira, D., Silva, S.: Applications of the multimodal interaction architecture in ambient assisted living. In: Dahl, D. (ed.) Multimodal Interaction with W3C Standards. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-42816-1_12"},{"key":"4_CR19","doi-asserted-by":"publisher","unstructured":"Teixeira, A., Almeida, N., Ketsmur, M., Silva, S.: Chapter 6 - effective natural interaction with our sensorized smart homes. In: Neustein, A. (ed.) Advances in Ubiquitous Computing. Advances in Ubiquitous Sensing Applications for Healthcare, pp. 185\u2013222. Academic Press (2020). https:\/\/doi.org\/10.1016\/B978-0-12-816801-1.00006-2","DOI":"10.1016\/B978-0-12-816801-1.00006-2"},{"key":"4_CR20","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/j.csl.2018.11.003","volume":"55","author":"A Thangthai","year":"2019","unstructured":"Thangthai, A., Milner, B., Taylor, S.: Synthesising visual speech using dynamic visemes and deep learning architectures. Comput. Speech Lang. 55, 101\u2013119 (2019)","journal-title":"Comput. Speech Lang."},{"issue":"1","key":"4_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-72375-y","volume":"10","author":"R Th\u00e9z\u00e9","year":"2020","unstructured":"Th\u00e9z\u00e9, R., Gadiri, M.A., Albert, L., Provost, A., Giraud, A.L., M\u00e9gevand, P.: Animated virtual characters to explore audio-visual speech in controlled and naturalistic environments. Sci. Rep. 10(1), 1\u201312 (2020)","journal-title":"Sci. Rep."}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87802-3_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T23:37:04Z","timestamp":1632267424000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87802-3_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030878016","9783030878023"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87802-3_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"22 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"St Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"163","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":"74","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":"45% - 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":"3.5","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":"5.5","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)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}