{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T22:10:10Z","timestamp":1755900610965,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,17]],"date-time":"2023-10-17T00:00:00Z","timestamp":1697500800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Provincial Natural Science Foundation of Ningxia","award":["No.2022AAC05040"],"award-info":[{"award-number":["No.2022AAC05040"]}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.61962002"],"award-info":[{"award-number":["No.61962002"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,17]]},"DOI":"10.1145\/3627915.3628019","type":"proceedings-article","created":{"date-parts":[[2023,12,21]],"date-time":"2023-12-21T12:07:00Z","timestamp":1703160420000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Conversational Discourse: A Framework for Collaborative Dialogue Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4422-3524","authenticated-orcid":false,"given":"Qiang","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, North Minzu University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3672-0193","authenticated-orcid":false,"given":"Zhibo","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, North Minzu University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0392-4582","authenticated-orcid":false,"given":"Zijin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, North Minzu University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8616-3075","authenticated-orcid":false,"given":"Qianyu","family":"Mai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, North Minzu University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2017-4334","authenticated-orcid":false,"given":"Wenxia","family":"Qiao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, North Minzu University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3459-2078","authenticated-orcid":false,"given":"Mingjuan","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Economics, North Minzu University, China"}]}],"member":"320","published-online":{"date-parts":[[2023,12,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462133"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817150"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1159\/000259969"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.392230"},{"issue":"6","key":"e_1_3_2_1_5_1","first-page":"598","article-title":"Hearing by eye: The psychology of lip-reading","volume":"72","author":"Dodd B.","year":"1987","unstructured":"B. Dodd and R. Campbell (1987). Hearing by eye: The psychology of lip-reading. American Journal of Psychology, 72(6), 598-602.","journal-title":"American Journal of Psychology"},{"key":"e_1_3_2_1_6_1","volume-title":"Proc. IEEE-CS Conference on Computer Vision and Pattern Recognition. 40-47","author":"Petajan E. D","year":"1985","unstructured":"E. D Petajan (1985). Automatic lipreading to enhance speech recognition. Proc. IEEE-CS Conference on Computer Vision and Pattern Recognition. 40-47."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1027933.1027960"},{"key":"e_1_3_2_1_8_1","volume-title":"2012 Proceedings of the 20th European Signal Processing Conference. 2714-2717","author":"Galatas G.","year":"2012","unstructured":"G. Galatas, G. Potamianos and F. Makedon (2012). Audio-visual speech recognition incorporating facial depth information captured by the Kinect. In 2012 Proceedings of the 20th European Signal Processing Conference. 2714-2717."},{"key":"e_1_3_2_1_9_1","volume-title":"Conference on Advances in Communication and Control Systems. 234-238","author":"Biswas A.","year":"2013","unstructured":"A. Biswas, P.K Sahu, A. Bhowmick and M. Chandra (2013). Audio visual isolated Oriya digit recognition using HMM and DWT. In Conference on Advances in Communication and Control Systems. 234-238."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521429"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053974"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/app10207263"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897235"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.9.5.753"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPICS55264.2022.9873574"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSCWD.2012.6221822"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383573"},{"key":"e_1_3_2_1_18_1","volume-title":"Perception of the visual environment","author":"Boothe R. G","year":"2001","unstructured":"R. G Boothe (2001). Perception of the visual environment. Springer Science & Business Media."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1152\/jn.2000.84.4.2048"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-51662-2"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/86.895946"},{"key":"e_1_3_2_1_22_1","volume-title":"Hearing lips in a second language: visual articulatory information enables the perception of second language sounds. Psychological research, 71, 4-12","author":"Navarra J","year":"2007","unstructured":"J Navarra and S Soto-Faraco (2007). Hearing lips in a second language: visual articulatory information enables the perception of second language sounds. Psychological research, 71, 4-12."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0507704102"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.00094"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23041834"},{"key":"e_1_3_2_1_26_1","volume-title":"Knowledge Mining Based Collaborative Framework for Manufacturing Value Chains. In 2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design. 847-854","author":"Qin B","year":"2022","unstructured":"B Qin, J Zhang, K Ma, P Peng and H Wang (2022). Knowledge Mining Based Collaborative Framework for Manufacturing Value Chains. In 2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design. 847-854."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-8701-9_2"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCMC53470.2022.9753792"},{"volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 4700-4708","author":"Huang G.","key":"e_1_3_2_1_29_1","unstructured":"G. Huang, Z. Liu, L. Van Der Maaten and K. Q. Weinberger (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4700-4708."},{"key":"e_1_3_2_1_30_1","volume-title":"O Vinyals and A Zisserman","author":"Afouras T","year":"2018","unstructured":"T Afouras, J.S Chung, A Senior, O Vinyals and A Zisserman (2018). Deep audio-visual speech recognition. IEEE transactions on pattern analysis and machine intelligence, 44(12), 8717-8727."},{"key":"e_1_3_2_1_31_1","volume-title":"Attention is all you need. Advances in neural information processing systems. 30","author":"Vaswani A","year":"2017","unstructured":"A Vaswani, N Shazeer, N Parmar, J Uszkoreit, L Jones, A.N Gomez and I Polosukhin (2017). Attention is all you need. Advances in neural information processing systems. 30."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.visinf.2018.04.011"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1669"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"e_1_3_2_1_36_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma D. P.","year":"2014","unstructured":"D. P. Kingma and J Ba (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"e_1_3_2_1_38_1","volume-title":"Z Li and Y Qiao","author":"Zhang K","year":"2016","unstructured":"K Zhang, Z Zhang, Z Li and Y Qiao (2016). Joint face detection and alignment using multitask cascaded convolutional networks. IEEE signal processing letters, 23(10), 1499-1503."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477558"},{"key":"e_1_3_2_1_40_1","volume-title":"Labeled faces in the wild: A database for studying face recognition in unconstrained environments","author":"Huang G. B.","year":"2008","unstructured":"G. B. Huang, M. Ramesh, T. Berg and E. Learned-Miller (2008). Labeled faces in the wild: A database for studying face recognition in unconstrained environments. University of Massachusetts, Amherst, Tech. 07-49."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE56475.2022.10014210"}],"event":{"name":"CSAE 2023: The 7th International Conference on Computer Science and Application Engineering","acronym":"CSAE 2023","location":"Virtual Event China"},"container-title":["Proceedings of the 7th International Conference on Computer Science and Application Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627915.3628019","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627915.3628019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T21:46:37Z","timestamp":1755899197000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627915.3628019"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,17]]},"references-count":41,"alternative-id":["10.1145\/3627915.3628019","10.1145\/3627915"],"URL":"https:\/\/doi.org\/10.1145\/3627915.3628019","relation":{},"subject":[],"published":{"date-parts":[[2023,10,17]]},"assertion":[{"value":"2023-12-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}