{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T05:44:45Z","timestamp":1781329485056,"version":"3.54.1"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T00:00:00Z","timestamp":1724803200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T00:00:00Z","timestamp":1724803200000},"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":[[2024,8,28]]},"DOI":"10.1109\/icac61394.2024.10718747","type":"proceedings-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T17:41:15Z","timestamp":1729705275000},"page":"1-6","source":"Crossref","is-referenced-by-count":5,"title":["SpeechCraft: An Integrated Data Generation Pipeline from Videos for LLM Finetuning"],"prefix":"10.1109","author":[{"given":"Jyothi Swaroop Arlagadda","family":"N","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Venkata Sai Mahesh","family":"Vuppalapati","sequence":"additional","affiliation":[{"name":"Tubi TV,San Fransisco,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shrey Dharmendra","family":"Modi","sequence":"additional","affiliation":[{"name":"California State University Long Beach,Long Beach,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahul","family":"Vishwakarma","sequence":"additional","affiliation":[{"name":"California State University Long Beach,Long Beach,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heer","family":"Shah","sequence":"additional","affiliation":[{"name":"California State University Long Beach,Long Beach,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","article-title":"Llm-enhanced data management","author":"Zhou","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657807"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1145\/3649329.3657356","article-title":"Data is all you need: Finetuning llms for chip design via an automated design-data augmentation framework","author":"Chang","year":"2024"},{"key":"ref5","article-title":"Sparql generation: an analysis on fine-tuning openllama for question answering over a life science knowledge graph","author":"Rangel","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW58026.2022.00078"},{"key":"ref7","article-title":"Automated data curation for robust language model fine-tuning","author":"Chen","year":"2024"},{"key":"ref8","author":"Tang","year":"2023","journal-title":"Does synthetic data generation of llms help clinical text mining"},{"key":"ref9","article-title":"Vimeo","year":"2024"},{"key":"ref10","article-title":"Facebook","year":"2024"},{"key":"ref11","article-title":"Instagram","year":"2024"},{"key":"ref12","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref13","article-title":"The refinedweb dataset for falcon llm: Outperforming curated corpora with web data, and web data only","author":"Penedo","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctv1tjrvk1.47"},{"key":"ref15","journal-title":"\\phi,\u201d a Greek letter, often used in scientific and mathematical contexts"},{"key":"ref16","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","volume":"31","author":"Zhang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Adadelta: an adaptive learning rate method","author":"Zeiler","year":"2012"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1968.10490530"}],"event":{"name":"2024 29th International Conference on Automation and Computing (ICAC)","location":"Sunderland, United Kingdom","start":{"date-parts":[[2024,8,28]]},"end":{"date-parts":[[2024,8,30]]}},"container-title":["2024 29th International Conference on Automation and Computing (ICAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10718699\/10718729\/10718747.pdf?arnumber=10718747","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T02:23:09Z","timestamp":1732674189000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10718747\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,28]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icac61394.2024.10718747","relation":{},"subject":[],"published":{"date-parts":[[2024,8,28]]}}}