{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:38:04Z","timestamp":1776357484935,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,4]]},"DOI":"10.1145\/3798065.3798087","type":"proceedings-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T19:30:21Z","timestamp":1775676621000},"page":"148-154","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Make a Video Call with LLM: A Measurement Campaign over Five Mainstream Apps"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7707-5273","authenticated-orcid":false,"given":"Jiayang","family":"Xu","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3834-8004","authenticated-orcid":false,"given":"Xiangjie","family":"Huang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7468-9624","authenticated-orcid":false,"given":"Zijie","family":"Li","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2009-7180","authenticated-orcid":false,"given":"Zili","family":"Meng","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jennifer Allen. 2021. 10 years of Siri: the history of Apple's voice assistant | TechRadar. https:\/\/www.techradar.com\/news\/siri- 10-year-anniversary. (2021)."},{"key":"e_1_3_2_1_2_1","unstructured":"Inc.) Amazon Web Services Inc. (a subsidiary of Amazon.com. 2006. AWS Cloud: Amazon Web Services - Comprehensive Cloud Computing Platform. https:\/\/aws.amazon.com\/. (2006)."},{"key":"e_1_3_2_1_3_1","volume-title":"Toward one-second latency: Evolution of live media streaming","author":"Bentaleb Abdelhak","year":"2025","unstructured":"Abdelhak Bentaleb, May Lim, Mehmet N Akcay, Ali C Begen, Sarra Hammoudi, and Roger Zimmermann. 2025. Toward one-second latency: Evolution of live media streaming. IEEE Communications Surveys & Tutorials (2025)."},{"key":"e_1_3_2_1_4_1","unstructured":"ByteDance. 2023. Doubao. https:\/\/doubao.com\/. (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3487552.3487847"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/VRW55335.2022.00040"},{"key":"e_1_3_2_1_7_1","unstructured":"Alibaba Cloud. 2009. Alibaba Cloud. https:\/\/www.alibabacloud.com\/. (2009)."},{"key":"e_1_3_2_1_8_1","volume-title":"Moshi: a speech-text foundation model for real-time dialogue. arXiv preprint arXiv:2410.00037","author":"D\u00e9fossez Alexandre","year":"2024","unstructured":"Alexandre D\u00e9fossez, Laurent Mazar\u00e9, Manu Orsini, Am\u00e9lie Royer, Patrick P\u00e9rez, Herv\u00e9 J\u00e9gou, Edouard Grave, and Neil Zeghidour. 2024. Moshi: a speech-text foundation model for real-time dialogue. arXiv preprint arXiv:2410.00037 (2024)."},{"key":"e_1_3_2_1_9_1","unstructured":"Pierre Nicolas Durette and Contributors. 2014. gTTS: Google Text-to-Speech. https:\/\/pypi.org\/project\/gTTS\/. (2014). Python library for interacting with Google's Text-to-Speech API."},{"key":"e_1_3_2_1_10_1","unstructured":"Genymotion. 2025. Professional Android Emulator. https:\/\/www.genymotion.com\/. (2025)."},{"key":"e_1_3_2_1_11_1","unstructured":"Google. 2025. Gemini Live with Camera. https:\/\/www.youtube.com\/watch?v=2Db6dBT6Vwg. (2025)."},{"key":"e_1_3_2_1_12_1","unstructured":"Google. 2025. Google Gemini. https:\/\/gemini.google.com\/. (2025)."},{"key":"e_1_3_2_1_13_1","unstructured":"Google. 2025. Pop Quiz Gemini Live with Camera. https:\/\/www.youtube.com\/shorts\/q78Z8ZEc3Cs. (2025)."},{"key":"e_1_3_2_1_14_1","unstructured":"Google. 2025. Project Astra | Exploring the Future of Learning with an AI Tutor Research Prototype. https:\/\/www.youtube.com\/watch?v=MQ4JfafE5Wo. (2025)."},{"key":"e_1_3_2_1_15_1","volume-title":"Project Astra: Our vision for the future of AI assistants. https:\/\/www.youtube.com\/shorts\/1ritVbXeMbg.","year":"2025","unstructured":"Google. 2025. Project Astra: Our vision for the future of AI assistants. https:\/\/www.youtube.com\/shorts\/1ritVbXeMbg. (2025)."},{"key":"e_1_3_2_1_16_1","unstructured":"Google. 2025. Spot a mystery bird? https:\/\/www.youtube.com\/watch?v=MjcpIuW5fG0. (2025)."},{"key":"e_1_3_2_1_17_1","unstructured":"Google. 2025. Wikipedia Rabbit Hole with screen share. https:\/\/www.yout.ube.com\/watch?v=MQ4jfafE5Wo. (2025)."},{"key":"e_1_3_2_1_18_1","unstructured":"Bloomberg Intelligence. 2025. Assessing Opportunities and Disruptions in an Evolving Trillion-Dollar Market. https:\/\/assets.bbhub.io\/promo\/sites\/16\/Bloomberg-Intelligence-NVDA-Gen-AIs-Disruptive-Race.pdf. (2025). Accessed: 2025-08-30."},{"key":"e_1_3_2_1_19_1","unstructured":"International Telecommunication Union Telecommunication Standardization Sector (ITU-T). 2003. One-way Transmission Time for the General Recommendations on the Transmission Quality for an Entire International Telephone Connection. Technical Report G.114. International Telecommunication Union (ITU). https:\/\/www.itu.int\/rec\/t-rec-g.114-200305-i ITU-T Recommendation G.114 (2003-05)."},{"key":"e_1_3_2_1_20_1","unstructured":"Inc. IPinfo.io. 2013. IPinfo.io: IP Address Data and Geolocation API. https:\/\/ipinfo.io\/. (2013)."},{"key":"e_1_3_2_1_21_1","volume-title":"Streamingbench: Assessing the gap for mllms to achieve streaming video understanding. arXiv preprint arXiv:2411.03628","author":"Lin Junming","year":"2024","unstructured":"Junming Lin, Zheng Fang, Chi Chen, Zihao Wan, Fuwen Luo, Peng Li, Yang Liu, and Maosong Sun. 2024. Streamingbench: Assessing the gap for mllms to achieve streaming video understanding. arXiv preprint arXiv:2411.03628 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"tc(8) \u2014 Linux manual page: show \/ manipulate traffic control settings. https:\/\/man7.org\/linux\/man-pages\/man8\/tc8.html. (2025). Accessed from the iproute2 project repository","author":"Linux","year":"2025","unstructured":"Linux man-pages project. 2025. tc(8) \u2014 Linux manual page: show \/ manipulate traffic control settings. https:\/\/man7.org\/linux\/man-pages\/man8\/tc8.html. (2025). Accessed from the iproute2 project repository; Last repository commitdate: 2025-08-08; HTML page retrieved: 2025-08-11. Documentation for the Linux kernel traffic control utility, covering qdiscs, classes, filters, and traffic shaping\/scheduling\/policing operations."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3487552.3487842"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"MaxMind. 2002. MaxMind. https:\/\/www.maxmind.com\/. (2002).","DOI":"10.1145\/504689.504690"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517745.3561414"},{"key":"e_1_3_2_1_26_1","unstructured":"OpenAI. 2022. ChatGPT. https:\/\/openai.com\/blog\/chatgpt\/. (2022)."},{"key":"e_1_3_2_1_27_1","unstructured":"QuestMobile. 2025. The number of mobile application users reaches 645 million. https:\/\/news.qq.com\/rain\/a\/20250916A02I7100. (2025). Accessed: 2025-08-30."},{"key":"e_1_3_2_1_28_1","volume-title":"Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever.","author":"Radford Alec","year":"2022","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2022. Robust Speech Recognition via Large-Scale Weak Supervision. (2022). arXiv:eess.AS\/2212.04356 https:\/\/arxiv.org\/abs\/2212.04356"},{"key":"e_1_3_2_1_29_1","volume-title":"The best AI chatbots","author":"Rebelo Miguel","year":"2025","unstructured":"Miguel Rebelo. 2025. The best AI chatbots in 2025. https:\/\/zapier.com\/blog\/best-ai-chatbot\/. (2025). Accessed: 2025-08-30."},{"key":"e_1_3_2_1_30_1","volume-title":"You can now do \u2018Live video","year":"1931","unstructured":"techkafever. 2025. You can now do \u2018Live video\u2019 with Google Gemini. https:\/\/x.com\/techkafever\/status\/1931961962214342989?referrer=grok-com. (2025)."},{"key":"e_1_3_2_1_31_1","unstructured":"Tencent. 2025. Tencent Yuanbao. https:\/\/yuanbao.tencent.com\/. (2025)."},{"key":"e_1_3_2_1_32_1","unstructured":"Unknown. 2025. VIDEO CONFERENCING MARKET ANALYSIS. https:\/\/www.fortunebusinessinsights.com\/industry-reports\/video-conferencing-market-100293. (2025). Accessed: 2025-08-30."},{"key":"e_1_3_2_1_33_1","unstructured":"Think with Google. 2025. A stroll in the sun with Gemini Live. https:\/\/x.com\/ThinkwithGoogle\/status\/1934971969054617605?referrer=grok-com. (2025)."},{"key":"e_1_3_2_1_34_1","unstructured":"xAI. 2025. Grok AI. https:\/\/grokdemo.com\/. (2025)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517745.3561464"},{"key":"e_1_3_2_1_36_1","volume-title":"Glm-4-voice: Towards intelligent and human-like end-to-end spoken chatbot. arXiv preprint arXiv:2412.02612","author":"Zeng Aohan","year":"2024","unstructured":"Aohan Zeng, Zhengxiao Du, Mingdao Liu, Kedong Wang, Shengmin Jiang, Lei Zhao, Yuxiao Dong, and Jie Tang. 2024. Glm-4-voice: Towards intelligent and human-like end-to-end spoken chatbot. arXiv preprint arXiv:2412.02612 (2024)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric Xing et al. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in neural information processing systems 36 (2023) 46595\u201346623.","DOI":"10.52202\/075280-2020"}],"event":{"name":"NOSSDAV '26: ACM Multimedia Systems Conference 2026","location":"Hong Kong Hong Kong","acronym":"NOSSDAV '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 36th Workshop on Network and Operating System Support for Digital Audio and Video"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3798065.3798087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T15:34:01Z","timestamp":1776353641000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3798065.3798087"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,4]]},"references-count":37,"alternative-id":["10.1145\/3798065.3798087","10.1145\/3798065"],"URL":"https:\/\/doi.org\/10.1145\/3798065.3798087","relation":{},"subject":[],"published":{"date-parts":[[2026,4,4]]},"assertion":[{"value":"2026-04-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}