{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T17:17:48Z","timestamp":1770830268268,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["No. 61832007, 61622403, 61621091, U19B2019"],"award-info":[{"award-number":["No. 61832007, 61622403, 61621091, U19B2019"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3413623","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T13:10:44Z","timestamp":1602508244000},"page":"1985-1993","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["DualLip"],"prefix":"10.1145","author":[{"given":"Weicong","family":"Chen","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Tan","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingce","family":"Xia","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Qin","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tie-Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"Triantafyllos Afouras Joon Son Chung and Andrew Zisserman. 2018. Deep lip reading: a comparison of models and an online application. arXiv preprint arXiv:1806.06053 (2018).  Triantafyllos Afouras Joon Son Chung and Andrew Zisserman. 2018. Deep lip reading: a comparison of models and an online application. arXiv preprint arXiv:1806.06053 (2018).","DOI":"10.21437\/Interspeech.2018-1943"},{"key":"e_1_3_2_2_2_1","volume-title":"Lipnet: End-to-end sentence-level lipreading. arXiv preprint arXiv:1611.01599","author":"Assael Yannis M","year":"2016"},{"key":"e_1_3_2_2_3_1","unstructured":"Dzmitry Bahdanau Kyunghyun Cho and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014).  Dzmitry Bahdanau Kyunghyun Cho and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Lele Chen Zhiheng Li Ross K Maddox Zhiyao Duan and Chenliang Xu. 2018. Lip Movements Generation at a Glance. (2018).  Lele Chen Zhiheng Li Ross K Maddox Zhiyao Duan and Chenliang Xu. 2018. Lip Movements Generation at a Glance. (2018).","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Mingjian Chen Xu Tan Yi Ren Jin Xu Hao Sun Sheng Zhao Tao Qin and Tie-Yan Liu. 2020. MultiSpeech: Multi-Speaker Text to Speech with Transformer. arXiv preprint arXiv:2006.04664 (2020).  Mingjian Chen Xu Tan Yi Ren Jin Xu Hao Sun Sheng Zhao Tao Qin and Tie-Yan Liu. 2020. MultiSpeech: Multi-Speaker Text to Speech with Transformer. arXiv preprint arXiv:2006.04664 (2020).","DOI":"10.21437\/Interspeech.2020-3139"},{"key":"e_1_3_2_2_6_1","unstructured":"Jan K Chorowski Dzmitry Bahdanau Dmitriy Serdyuk Kyunghyun Cho and Yoshua Bengio. 2015. Attention-based models for speech recognition. In Advances in neural information processing systems. 577--585.  Jan K Chorowski Dzmitry Bahdanau Dmitriy Serdyuk Kyunghyun Cho and Yoshua Bengio. 2015. Attention-based models for speech recognition. In Advances in neural information processing systems. 577--585."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Joon Son Chung Amir Jamaludin and Andrew Zisserman. 2017a. You said that? arXiv preprint arXiv:1705.02966 (2017).  Joon Son Chung Amir Jamaludin and Andrew Zisserman. 2017a. You said that? arXiv preprint arXiv:1705.02966 (2017).","DOI":"10.5244\/C.31.109"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"e_1_3_2_2_9_1","volume-title":"Asian Conference on Computer Vision. Springer, 87--103","author":"Chung Joon Son","year":"2016"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323028"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"e_1_3_2_2_14_1","unstructured":"Di He Yingce Xia Tao Qin Liwei Wang Nenghai Yu Tie-Yan Liu and Wei-Ying Ma. 2016a. Dual learning for machine translation. In Advances in neural information processing systems. 820--828.  Di He Yingce Xia Tao Qin Liwei Wang Nenghai Yu Tie-Yan Liu and Wei-Ying Ma. 2016a. Dual learning for machine translation. In Advances in neural information processing systems. 820--828."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"e_1_3_2_2_18_1","volume-title":"Dlib-ml: A Machine Learning Toolkit. JMLR.org.","author":"King Davis E.","year":"2009"},{"key":"e_1_3_2_2_19_1","volume-title":"Adam: A Method for Stochastic Optimization. Computer Science","author":"Kingma Diederik","year":"2014"},{"key":"e_1_3_2_2_20_1","volume-title":"Proceedings of the 27th ACM International Conference on Multimedia. 1428--1436","author":"Rudrabha Mukhopadhyay Prajwal KR","year":"2019"},{"key":"e_1_3_2_2_21_1","volume-title":"Obamanet: Photo-realistic lip-sync from text. arXiv preprint arXiv:1801.01442","author":"Kumar Rithesh","year":"2017"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350986"},{"key":"e_1_3_2_2_23_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled Weight Decay Regularization. (2017).  Ilya Loshchilov and Frank Hutter. 2017. Decoupled Weight Decay Regularization. (2017)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"crossref","unstructured":"Brais Martinez Pingchuan Ma Stavros Petridis and Maja Pantic. 2020. Lipreading using Temporal Convolutional Networks. arXiv preprint arXiv:2001.08702 (2020).  Brais Martinez Pingchuan Ma Stavros Petridis and Maja Pantic. 2020. Lipreading using Temporal Convolutional Networks. arXiv preprint arXiv:2001.08702 (2020).","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"e_1_3_2_2_25_1","volume-title":"Nature","volume":"264","author":"McGurk Harry","year":"1976"},{"key":"e_1_3_2_2_26_1","volume-title":"Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499","author":"van den Oord Aaron","year":"2016"},{"key":"e_1_3_2_2_27_1","volume-title":"Advances in Neural Information Processing Systems 32, H. Wallach, H. Larochelle, A. Beygelzimer, F. dtextquotesingle Alch\u00e9-Buc","author":"Paszke Adam"},{"key":"e_1_3_2_2_28_1","volume-title":"Interspeech","author":"Qu Leyuan","year":"2019"},{"key":"e_1_3_2_2_29_1","unstructured":"Yi Ren Chenxu Hu Xu Tan Tao Qin Sheng Zhao Zhou Zhao and Tie-Yan Liu. 2020. FastSpeech 2: Fast and High-Quality End-to-End Text-to-Speech. arXiv preprint arXiv:2006.04558 (2020).  Yi Ren Chenxu Hu Xu Tan Tao Qin Sheng Zhao Zhou Zhao and Tie-Yan Liu. 2020. FastSpeech 2: Fast and High-Quality End-to-End Text-to-Speech. arXiv preprint arXiv:2006.04558 (2020)."},{"key":"e_1_3_2_2_30_1","unstructured":"Yi Ren Yangjun Ruan Xu Tan Tao Qin Sheng Zhao Zhou Zhao and Tie-Yan Liu. 2019 a. Fastspeech: Fast robust and controllable text to speech. In Advances in Neural Information Processing Systems. 3165--3174.  Yi Ren Yangjun Ruan Xu Tan Tao Qin Sheng Zhao Zhou Zhao and Tie-Yan Liu. 2019 a. Fastspeech: Fast robust and controllable text to speech. In Advances in Neural Information Processing Systems. 3165--3174."},{"key":"e_1_3_2_2_31_1","volume-title":"International Conference on Machine Learning. 5410--5419","author":"Ren Yi","year":"2019"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Yang Song Jingwen Zhu Dawei Li Xiaolong Wang and Hairong Qi. 2018. Talking face generation by conditional recurrent adversarial network. arXiv preprint arXiv:1804.04786 (2018).  Yang Song Jingwen Zhu Dawei Li Xiaolong Wang and Hairong Qi. 2018. Talking face generation by conditional recurrent adversarial network. arXiv preprint arXiv:1804.04786 (2018).","DOI":"10.24963\/ijcai.2019\/129"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"e_1_3_2_2_36_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472852"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"crossref","unstructured":"Zhou Wang. 2004. Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Transactions on Image Processing (2004).  Zhou Wang. 2004. Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Transactions on Image Processing (2004).","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"Jin Xu Xu Tan Yi Ren Tao Qin Jian Li Sheng Zhao and Tie-Yan Liu. 2020. LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition. arXiv preprint arXiv:2008.03687 (2020).  Jin Xu Xu Tan Yi Ren Tao Qin Jian Li Sheng Zhao and Tie-Yan Liu. 2020. LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition. arXiv preprint arXiv:2008.03687 (2020).","DOI":"10.1145\/3394486.3403331"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00088"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00089"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.2935783"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"Heiga Zen Viet Dang Rob Clark Yu Zhang Ron J Weiss Ye Jia Zhifeng Chen and Yonghui Wu. 2019. LibriTTS: A corpus derived from librispeech for text-to-speech. arXiv preprint arXiv:1904.02882 (2019).  Heiga Zen Viet Dang Rob Clark Yu Zhang Ron J Weiss Ye Jia Zhifeng Chen and Yonghui Wu. 2019. LibriTTS: A corpus derived from librispeech for text-to-speech. arXiv preprint arXiv:1904.02882 (2019).","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132920"},{"key":"e_1_3_2_2_46_1","unstructured":"Ruobing Zheng Zhou Zhu Bo Song and Changjiang Ji. 2020. Photorealistic Lip Sync with Adversarial Temporal Convolutional Networks. arXiv preprint arXiv:2002.08700 (2020).  Ruobing Zheng Zhou Zhu Bo Song and Changjiang Ji. 2020. Photorealistic Lip Sync with Adversarial Temporal Convolutional Networks. arXiv preprint arXiv:2002.08700 (2020)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"e_1_3_2_2_48_1","unstructured":"Hao Zhu Mandi Luo Rui Wang Aihua Zheng and Ran He. 2020. Deep Audio-Visual Learning: A Survey. arXiv preprint arXiv:2001.04758 (2020).  Hao Zhu Mandi Luo Rui Wang Aihua Zheng and Ran He. 2020. Deep Audio-Visual Learning: A Survey. arXiv preprint arXiv:2001.04758 (2020)."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA","acronym":"MM '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413623","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:15Z","timestamp":1750193235000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413623"}},"subtitle":["A System for Joint Lip Reading and Generation"],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":49,"alternative-id":["10.1145\/3394171.3413623","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413623","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}