{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T13:51:25Z","timestamp":1781099485163,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,9,28]],"date-time":"2020-09-28T00:00:00Z","timestamp":1601251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,9,28]]},"DOI":"10.1145\/3399715.3399852","type":"proceedings-article","created":{"date-parts":[[2020,10,2]],"date-time":"2020-10-02T23:52:27Z","timestamp":1601682747000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["TieLent"],"prefix":"10.1145","author":[{"given":"Naoki","family":"Kimura","sequence":"first","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kentaro","family":"Hayashi","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Rekimoto","sequence":"additional","affiliation":[{"name":"The University of Tokyo Sony Computer Science Laboratories Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,10,2]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Coral. https:\/\/coral.withgoogle.com\/. (Accessed on 09\/20\/2019).  Coral. https:\/\/coral.withgoogle.com\/. (Accessed on 09\/20\/2019)."},{"key":"e_1_3_2_1_2_1","unstructured":"Custom Speech. https:\/\/speech.microsoft.com\/customspeech. (Accessed on 05\/30\/2020).  Custom Speech. https:\/\/speech.microsoft.com\/customspeech. (Accessed on 05\/30\/2020)."},{"key":"e_1_3_2_1_3_1","unstructured":"GTK+ UVC Viewer. http:\/\/guvcview.sourceforge.net\/. (Accessed on 09\/20\/2019).  GTK+ UVC Viewer. http:\/\/guvcview.sourceforge.net\/. (Accessed on 09\/20\/2019)."},{"key":"e_1_3_2_1_4_1","unstructured":"T. Afouras J. S. Chung A. Senior O. Vinyals and A. Zisserman. 2018. Deep Audio-Visual Speech Recognition. In arXiv:1809.02108.  T. Afouras J. S. Chung A. Senior O. Vinyals and A. Zisserman. 2018. Deep Audio-Visual Speech Recognition. In arXiv:1809.02108."},{"key":"e_1_3_2_1_5_1","volume-title":"Lip2AudSpec: Speech reconstruction from silent lip movements video. arXiv preprint arXiv: 1710.09798","author":"Akbari Hassan","year":"2017","unstructured":"Hassan Akbari , Himani Arora , Liangliang Cao , and Nima Mesgarani . 2017. Lip2AudSpec: Speech reconstruction from silent lip movements video. arXiv preprint arXiv: 1710.09798 ( 2017 ). Hassan Akbari, Himani Arora, Liangliang Cao, and Nima Mesgarani. 2017. Lip2AudSpec: Speech reconstruction from silent lip movements video. arXiv preprint arXiv: 1710.09798 (2017)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163155"},{"key":"e_1_3_2_1_7_1","volume-title":"LipNet: Sentence-level Lipreading. CoRR abs\/1611.01599","author":"Assael Yannis M.","year":"2016","unstructured":"Yannis M. Assael , Brendan Shillingford , Shimon Whiteson , and Nando de Freitas . 2016. LipNet: Sentence-level Lipreading. CoRR abs\/1611.01599 ( 2016 ). arXiv:1611.01599 http:\/\/arxiv.org\/abs\/1611.01599 Yannis M. Assael, Brendan Shillingford, Shimon Whiteson, and Nando de Freitas. 2016. LipNet: Sentence-level Lipreading. CoRR abs\/1611.01599 (2016). arXiv:1611.01599 http:\/\/arxiv.org\/abs\/1611.01599"},{"key":"e_1_3_2_1_8_1","volume-title":"Real-Time Control of an Articulatory-Based Speech Synthesizer for Brain Computer Interfaces. PLOS Computational Biology 12, 11 (11","author":"Bocquelet Florent","year":"2016","unstructured":"Florent Bocquelet , Thomas Hueber , Laurent Girin , Christophe Savariaux , and Blaise Yvert . 2016. Real-Time Control of an Articulatory-Based Speech Synthesizer for Brain Computer Interfaces. PLOS Computational Biology 12, 11 (11 2016 ), 1--28. https:\/\/doi.org\/10.1371\/journal.pcbi.1005119 10.1371\/journal.pcbi.1005119 Florent Bocquelet, Thomas Hueber, Laurent Girin, Christophe Savariaux, and Blaise Yvert. 2016. Real-Time Control of an Articulatory-Based Speech Synthesizer for Brain Computer Interfaces. PLOS Computational Biology 12, 11 (11 2016), 1--28. https:\/\/doi.org\/10.1371\/journal.pcbi.1005119"},{"key":"e_1_3_2_1_9_1","volume-title":"Lip Reading Sentences in the Wild. CoRR abs\/1611.05358","author":"Chung Joon Son","year":"2016","unstructured":"Joon Son Chung , Andrew W. Senior , Oriol Vinyals , and Andrew Zisserman . 2016. Lip Reading Sentences in the Wild. CoRR abs\/1611.05358 ( 2016 ). arXiv:1611.05358 http:\/\/arxiv.org\/abs\/1611.05358 Joon Son Chung, Andrew W. Senior, Oriol Vinyals, and Andrew Zisserman. 2016. Lip Reading Sentences in the Wild. CoRR abs\/1611.05358 (2016). arXiv:1611.05358 http:\/\/arxiv.org\/abs\/1611.05358"},{"key":"e_1_3_2_1_10_1","volume-title":"An audiovisual corpus for speech perception and automatic speech recognition (L). The Journal of the Acoustical Society of America 120 (12","author":"Cooke Martin","year":"2006","unstructured":"Martin Cooke , Jon Barker , Stuart Cunningham , and Xu Shao . 2006. An audiovisual corpus for speech perception and automatic speech recognition (L). The Journal of the Acoustical Society of America 120 (12 2006 ), 2421--4. https:\/\/doi.org\/10.1121\/1.2229005 10.1121\/1.2229005 Martin Cooke, Jon Barker, Stuart Cunningham, and Xu Shao. 2006. An audiovisual corpus for speech perception and automatic speech recognition (L). The Journal of the Acoustical Society of America 120 (12 2006), 2421--4. https:\/\/doi.org\/10.1121\/1.2229005"},{"key":"e_1_3_2_1_11_1","unstructured":"Tam\u00e1s G\u00e1bor Csap\u00f3 Tam\u00e1s Gr\u00f3sz G\u00e1bor Gosztolya L\u00e1szl\u00f3 T\u00f3th and Alexandra Mark\u00f3. 2017. DNN-Based Ultrasound-to-Speech Conversion for a Silent Speech Interface. In INTERSPEECH.  Tam\u00e1s G\u00e1bor Csap\u00f3 Tam\u00e1s Gr\u00f3sz G\u00e1bor Gosztolya L\u00e1szl\u00f3 T\u00f3th and Alexandra Mark\u00f3. 2017. DNN-Based Ultrasound-to-Speech Conversion for a Silent Speech Interface. In INTERSPEECH."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/3104482.3104599"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.medengphy.2007.05.003"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242603"},{"key":"e_1_3_2_1_17_1","volume-title":"Moore","author":"Gonzalez Jose A.","year":"2016","unstructured":"Jose A. Gonzalez , Lam A. Cheah , James M. Gilbert , Jie Bai , Stephen R. Ell , Phil D. Green , and Roger K . Moore . 2016 . A Silent Speech System Based on Permanent Magnet Articulography and Direct Synthesis. Comput. Speech Lang. 39, C (Sept . 2016), 67--87. https:\/\/doi.org\/10.1016\/j.csl.2016.02.002 10.1016\/j.csl.2016.02.002 Jose A. Gonzalez, Lam A. Cheah, James M. Gilbert, Jie Bai, Stephen R. Ell, Phil D. Green, and Roger K. Moore. 2016. A Silent Speech System Based on Permanent Magnet Articulography and Direct Synthesis. Comput. Speech Lang. 39, C (Sept. 2016), 67--87. https:\/\/doi.org\/10.1016\/j.csl.2016.02.002"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"#cr-split#-e_1_3_2_1_19_1.1","doi-asserted-by":"crossref","unstructured":"Tam\u00e1s Gr\u00f3sz G\u00e1bor Gosztolya L\u00e1szl\u00f3 T\u00f3th Tam\u00e1s Csap\u00f3 and Alexandra Mark\u00f3. 2018. F0 Estimation for DNN-Based Ultrasound Silent Speech Interfaces. https:\/\/doi.org\/10.1109\/ICASSP.2018.8461732 10.1109\/ICASSP.2018.8461732","DOI":"10.1109\/ICASSP.2018.8461732"},{"key":"#cr-split#-e_1_3_2_1_19_1.2","doi-asserted-by":"crossref","unstructured":"Tam\u00e1s Gr\u00f3sz G\u00e1bor Gosztolya L\u00e1szl\u00f3 T\u00f3th Tam\u00e1s Csap\u00f3 and Alexandra Mark\u00f3. 2018. F0 Estimation for DNN-Based Ultrasound Silent Speech Interfaces. https:\/\/doi.org\/10.1109\/ICASSP.2018.8461732","DOI":"10.1109\/ICASSP.2018.8461732"},{"key":"e_1_3_2_1_20_1","volume-title":"High-Speed Tracking with Kernelized Correlation Filters. CoRR abs\/1404.7584","author":"Henriques Jo\u00e3o F.","year":"2014","unstructured":"Jo\u00e3o F. Henriques , Rui Caseiro , Pedro Martins , and Jorge Batista . 2014. High-Speed Tracking with Kernelized Correlation Filters. CoRR abs\/1404.7584 ( 2014 ). arXiv:1404.7584 http:\/\/arxiv.org\/abs\/1404.7584 Jo\u00e3o F. Henriques, Rui Caseiro, Pedro Martins, and Jorge Batista. 2014. High-Speed Tracking with Kernelized Correlation Filters. CoRR abs\/1404.7584 (2014). arXiv:1404.7584 http:\/\/arxiv.org\/abs\/1404.7584"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.12.001"},{"key":"e_1_3_2_1_22_1","volume-title":"Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis. CoRR abs\/1704.04086","author":"Huang Rui","year":"2017","unstructured":"Rui Huang , Shu Zhang , Tianyu Li , and Ran He. 2017. Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis. CoRR abs\/1704.04086 ( 2017 ). arXiv:1704.04086 http:\/\/arxiv.org\/abs\/1704.04086 Rui Huang, Shu Zhang, Tianyu Li, and Ran He. 2017. Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis. CoRR abs\/1704.04086 (2017). arXiv:1704.04086 http:\/\/arxiv.org\/abs\/1704.04086"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366140"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.11.004"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.02.002"},{"key":"#cr-split#-e_1_3_2_1_26_1.1","doi-asserted-by":"crossref","unstructured":"Arnav Kapur Shreyas Kapur and Pattie Maes. 2018. AlterEgo: A Personalized Wearable Silent Speech Interface. 43--53. https:\/\/doi.org\/10.1145\/3172944.3172977 10.1145\/3172944.3172977","DOI":"10.1145\/3172944.3172977"},{"key":"#cr-split#-e_1_3_2_1_26_1.2","doi-asserted-by":"crossref","unstructured":"Arnav Kapur Shreyas Kapur and Pattie Maes. 2018. AlterEgo: A Personalized Wearable Silent Speech Interface. 43--53. https:\/\/doi.org\/10.1145\/3172944.3172977","DOI":"10.1145\/3172944.3172977"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2018.00-19"},{"key":"#cr-split#-e_1_3_2_1_28_1.1","doi-asserted-by":"crossref","unstructured":"Richard Li Jason Wu and Thad Starner. 2019. TongueBoard: An Oral Interface for Subtle Input. 1--9. https:\/\/doi.org\/10.1145\/3311823.3311831 10.1145\/3311823.3311831","DOI":"10.1145\/3311823.3311831"},{"key":"#cr-split#-e_1_3_2_1_28_1.2","doi-asserted-by":"crossref","unstructured":"Richard Li Jason Wu and Thad Starner. 2019. TongueBoard: An Oral Interface for Subtle Input. 1--9. https:\/\/doi.org\/10.1145\/3311823.3311831","DOI":"10.1145\/3311823.3311831"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566521"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.982900"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aac965"},{"key":"e_1_3_2_1_32_1","volume-title":"Distance measures for speech recognition, psychological and instrumental. Pattern Recognition and Artificial Intelligence","author":"P. MERMELSTEIN.","year":"1976","unstructured":"P. MERMELSTEIN. 1976. Distance measures for speech recognition, psychological and instrumental. Pattern Recognition and Artificial Intelligence ( 1976 ), 374--388. https:\/\/ci.nii.ac.jp\/naid\/10026808024\/ P. MERMELSTEIN. 1976. Distance measures for speech recognition, psychological and instrumental. Pattern Recognition and Artificial Intelligence (1976), 374--388. https:\/\/ci.nii.ac.jp\/naid\/10026808024\/"},{"key":"e_1_3_2_1_33_1","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 5, V - 708","author":"Nakajima Y","year":"2003","unstructured":"Y Nakajima , Hideki Kashioka , Kiyohiro Shikano , and Nick Campbell . 2003 . Non-audible murmur recognition input interface using stethoscopic microphone attached to the skin. ICASSP , IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 5, V - 708 . https:\/\/doi.org\/10.1109\/ICASSP.2003.1200069 10.1109\/ICASSP.2003.1200069 Y Nakajima, Hideki Kashioka, Kiyohiro Shikano, and Nick Campbell. 2003. Non-audible murmur recognition input interface using stethoscopic microphone attached to the skin. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 5, V - 708. https:\/\/doi.org\/10.1109\/ICASSP.2003.1200069"},{"key":"e_1_3_2_1_34_1","volume-title":"An Ultrasound Imaging-Based Silent Speech Interaction Using Deep Neural Networks. CHI2019","author":"Naoki Kimura Jun Rekimoto","year":"2019","unstructured":"Jun Rekimoto Naoki Kimura , Michinari Kono . 2019 . An Ultrasound Imaging-Based Silent Speech Interaction Using Deep Neural Networks. CHI2019 . Jun Rekimoto Naoki Kimura, Michinari Kono. 2019. An Ultrasound Imaging-Based Silent Speech Interaction Using Deep Neural Networks. CHI2019."},{"key":"e_1_3_2_1_36_1","volume-title":"Lipper: Speaker Independent Speech Synthesis using Multi-View Lipreading. In AAAI.","author":"Shah Zimmermann Salik Jain Aggarwal","year":"2019","unstructured":"Jain Aggarwal Shah Zimmermann Salik , Kumar. 2019 . Lipper: Speaker Independent Speech Synthesis using Multi-View Lipreading. In AAAI. Jain Aggarwal Shah Zimmermann Salik, Kumar. 2019. Lipper: Speaker Independent Speech Synthesis using Multi-View Lipreading. In AAAI."},{"key":"#cr-split#-e_1_3_2_1_37_1.1","doi-asserted-by":"crossref","unstructured":"Tanja Schultz. 2010. ICCHP Keynote: Recognizing Silent and Weak Speech Based on Electromyography. 595--604. https:\/\/doi.org\/10.1007\/978-3-642-14097-6_96 10.1007\/978-3-642-14097-6_96","DOI":"10.1007\/978-3-642-14097-6_96"},{"key":"#cr-split#-e_1_3_2_1_37_1.2","doi-asserted-by":"crossref","unstructured":"Tanja Schultz. 2010. ICCHP Keynote: Recognizing Silent and Weak Speech Based on Electromyography. 595--604. https:\/\/doi.org\/10.1007\/978-3-642-14097-6_96","DOI":"10.1007\/978-3-642-14097-6_96"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242599"},{"key":"e_1_3_2_1_39_1","volume-title":"Lipreading with Long Short-Term Memory. CoRR abs\/1601.08188","author":"Wand Michael","year":"2016","unstructured":"Michael Wand , Jan Koutn\u00edk , and J\u00fcrgen Schmidhuber . 2016. Lipreading with Long Short-Term Memory. CoRR abs\/1601.08188 ( 2016 ). arXiv:1601.08188 http:\/\/arxiv.org\/abs\/1601.08188 Michael Wand, Jan Koutn\u00edk, and J\u00fcrgen Schmidhuber. 2016. Lipreading with Long Short-Term Memory. CoRR abs\/1601.08188 (2016). arXiv:1601.08188 http:\/\/arxiv.org\/abs\/1601.08188"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.004"}],"event":{"name":"AVI '20: International Conference on Advanced Visual Interfaces","location":"Salerno Italy","acronym":"AVI '20","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","ACM Association for Computing Machinery","SIGMM ACM Special Interest Group on Multimedia","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the International Conference on Advanced Visual Interfaces"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3399715.3399852","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3399715.3399852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:31:49Z","timestamp":1750195909000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3399715.3399852"}},"subtitle":["A Casual Neck-Mounted Mouth Capturing Device for Silent Speech Interaction"],"short-title":[],"issued":{"date-parts":[[2020,9,28]]},"references-count":43,"alternative-id":["10.1145\/3399715.3399852","10.1145\/3399715"],"URL":"https:\/\/doi.org\/10.1145\/3399715.3399852","relation":{},"subject":[],"published":{"date-parts":[[2020,9,28]]},"assertion":[{"value":"2020-10-02","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}