{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:54:16Z","timestamp":1772934856687,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11400775","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"7012-7020","source":"Crossref","is-referenced-by-count":0,"title":["Asynchronous Pipeline Parallelism for Real-Time Multilingual Lip Synchronization in Video Communication Systems"],"prefix":"10.1109","author":[{"given":"Eren","family":"Caglar","sequence":"first","affiliation":[{"name":"Yildiz Technical University,Department of Data Science and Big Data,Istanbul,Turkey"}]},{"given":"Amirkia Rafiei","family":"Oskooei","sequence":"additional","affiliation":[{"name":"Yildiz Technical University,Department of Computer Engineering,Istanbul,Turkey"}]},{"given":"Mehmet","family":"Kutanoglu","sequence":"additional","affiliation":[{"name":"R&D Center, Aktif Investment Bank Inc.,Istanbul,Turkey"}]},{"given":"Mustafa","family":"Keles","sequence":"additional","affiliation":[{"name":"R&D Center, Aktif Investment Bank Inc.,Istanbul,Turkey"}]},{"given":"Mehmet S.","family":"Aktas","sequence":"additional","affiliation":[{"name":"Yildiz Technical University,Department of Computer Engineering,Istanbul,Turkey"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10606-022-09451-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/srep46413"},{"key":"ref3","article-title":"A lip sync expert is all you need for speech to lip generation in the wild","volume":"abs\/2008.10010","author":"Prajwal","year":"2020","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.14778\/3357377.3357383"},{"key":"ref5","article-title":"Listen, attend and spell","volume":"abs\/1508.01211","author":"Chan","year":"2015","journal-title":"CoRR"},{"key":"ref6","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume":"abs\/1512.02595","author":"Amodei","year":"2015","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref8","author":"Gulati","year":"2020","journal-title":"Conformer: Convolution-augmented transformer for speech recognition"},{"key":"ref9","article-title":"Sequence to sequence learning with neural networks","volume":"abs\/1409.3215","author":"Sutskever","year":"2014","journal-title":"CoRR"},{"issue":"09","key":"ref10","volume":"1409","author":"Bahdanau","year":"2014","journal-title":"Neural machine translation by jointly learning to align and translate"},{"key":"ref11","article-title":"Effective approaches to attention-based neural machine translation","volume":"abs\/1508.04025","author":"Luong","year":"2015","journal-title":"CoRR"},{"key":"ref12","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","volume":"abs\/1703.10135","author":"Wang","year":"2017","journal-title":"CoRR"},{"key":"ref13","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"abs\/1905.09263","author":"Ren","year":"2019","journal-title":"CoRR"},{"key":"ref14","author":"Ren","year":"2022","journal-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech"},{"key":"ref15","article-title":"Yourtts: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume":"abs\/2112.02418","author":"Casanova","year":"2021","journal-title":"CoRR"},{"key":"ref16","author":"Rubenstein","year":"2023","journal-title":"Audiopalm: A large language model that can speak and listen"},{"key":"ref17","volume":"abs\/2312.05187","author":"Communication","year":"2023","journal-title":"Seamless: Multilingual expressive and streaming speech translation"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref19","author":"Mukhopadhyay","year":"2023","journal-title":"Diff2lip: Audio conditioned diffusion models for lip-synchronization"},{"key":"ref20","author":"Li","year":"2025","journal-title":"Latentsync: Taming audio-conditioned latent diffusion models for lip sync with syncnet supervision"},{"key":"ref21","article-title":"Ad-nerf: Audio driven neural radiance fields for talking head synthesis","volume":"abs\/2103.11078","author":"Guo","year":"2021","journal-title":"CoRR"},{"key":"ref22","author":"Peng","year":"2024","journal-title":"Synctalk: The devil is in the synchronization for talking head synthesis"},{"key":"ref23","author":"Su","year":"2025","journal-title":"A bridge from audio to video: Phoneme-viseme alignment allows every face to speak multiple languages"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12552"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193719"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746421"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-97606-3_15"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.485"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3746059.3747722"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s00024-006-0137-8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/GRID.2005.1542750"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1199"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-09156-3_35"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1142\/S0218194016500133"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58811-3_65"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1142\/S0218194021500480"},{"key":"ref38","article-title":"Opus-mt - building open translation services for the world","volume-title":"European Association for Machine Translation Conferences\/Workshops","author":"Tiedemann","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-023-09704-w"},{"key":"ref40","volume":"abs\/2406.04904","author":"Casanova","year":"2024","journal-title":"Xtts: a massively multilingual zero-shot text-to-speech model"},{"key":"ref41","article-title":"S3fd: Single shot scale-invariant face detector","volume":"abs\/1708.05237","author":"Zhang","year":"2017","journal-title":"CoRR"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11400775.pdf?arnumber=11400775","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:18:42Z","timestamp":1772867922000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11400775\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11400775","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}