{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:05:53Z","timestamp":1740099953971,"version":"3.37.3"},"reference-count":61,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,10]]},"DOI":"10.1109\/bigdata50022.2020.9378438","type":"proceedings-article","created":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T21:10:21Z","timestamp":1616188221000},"page":"1939-1948","source":"Crossref","is-referenced-by-count":1,"title":["A Study of Spoken Audio Processing using Machine Learning for Libraries, Archives and Museums (LAM)"],"prefix":"10.1109","author":[{"given":"Weijia","family":"Xu","sequence":"first","affiliation":[]},{"given":"Maria","family":"Esteva","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Cui","sequence":"additional","affiliation":[]},{"given":"Eugene","family":"Castillo","sequence":"additional","affiliation":[]},{"given":"Kewen","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Hanna-Robbins","family":"Hopkins","sequence":"additional","affiliation":[]},{"given":"Tanya","family":"Clement","sequence":"additional","affiliation":[]},{"given":"Aaron","family":"Choate","sequence":"additional","affiliation":[]},{"given":"Ruizhu","family":"Huang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2014-80","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/89.260359"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/72.286885"},{"article-title":"FUNDAMENTAL TECHNOLOGIES IN MODERN SPEECH RECOGNITION","year":"2012","author":"senior","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"6645","DOI":"10.1109\/ICASSP.2013.6638947","article-title":"Speech recognition with deep recurrent neural networks","author":"graves","year":"2013","journal-title":"2013 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"ref60","first-page":"169","article-title":"A Framework for Speech Recognition Benchmarking","author":"dernoncourt","year":"2018","journal-title":"InterSpeech"},{"journal-title":"Good Systems Bridging Barriers Program","year":"0","key":"ref61"},{"key":"ref28","article-title":"A New hybrid algorithm for speech recognition based on HMM segmentation and learning Vector quantization","volume":"1","author":"katagiri","year":"0","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.899285"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40585-3_6"},{"key":"ref2","article-title":"Towards Affordable Disclosure of Spoken Heritage Archives","volume":"10","author":"ordelman","year":"2009","journal-title":"Journal of Digital Information"},{"key":"ref1","article-title":"Audio-visual Collections and the User Needs of Scholars in the Humanities: a Case for Co-Development","author":"de jong","year":"2011","journal-title":"Proceedings of the 2nd Conference on Supporting Digital Humanities (SDH 2011) (SDH 2011)"},{"journal-title":"Feasibility of Applying Off-the-Shelf Artificial Intelligence Tools on Digital Library Images Collections – Open Repositories 2021","year":"0","author":"maringanti","key":"ref20"},{"journal-title":"Always Already Computational - Collections as Data","article-title":"The Santa Barbara Statement on Collections as Data","year":"0","key":"ref22"},{"year":"0","key":"ref21","article-title":"Collections as Data -Part to Whole"},{"key":"ref24","article-title":"Twenty things we still don’t know about speech","author":"moore","year":"1994","journal-title":"Proc CRIM\/ FORWISS Workshop on Progress and Prospects of speech Research an Technology"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1109\/PROC.1976.10158","article-title":"speech recognition by machine: a review","volume":"64","author":"reddy","year":"1976","journal-title":"Proceedings of the IEEE"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.894524"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.905151"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1608"},{"journal-title":"Captioning and Transcription Services","year":"0","key":"ref51"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(01)00041-3"},{"journal-title":"The AFS Ethnographic Thesaurus","year":"0","key":"ref58"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071"},{"article-title":"The Dataset Nutrition Label: A Framework To Drive Higher Data Quality Standards","year":"2018","author":"holland","key":"ref56"},{"journal-title":"Speech to Text Web Service","year":"0","key":"ref55"},{"journal-title":"DeepSpeech Model performance","year":"0","key":"ref54"},{"key":"ref53","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"12th USENIX Symposium on Operating Systems Design and Implementation ( OSDI 16)"},{"journal-title":"DeepSpeech","year":"2020","key":"ref52"},{"key":"ref10","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"International Conference on Machine Learning"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref11"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.03.058"},{"journal-title":"StoryCorps Historias","year":"0","key":"ref12"},{"journal-title":"StoryCorps and AI 4 AV Team Interview","year":"2019","author":"millington","key":"ref13"},{"journal-title":"Responsible Operations Data Science Machine Learning and AI in Libraries","year":"2019","author":"padilla","key":"ref14"},{"journal-title":"SAA Core Values Statement and Code of Ethics | Society of American Archivists","year":"2020","key":"ref15"},{"journal-title":"Computational Archival Science","article-title":"Computational Archival Science","year":"0","key":"ref16"},{"year":"0","key":"ref17","article-title":"Transcribing the Allen Ginsberg Tapes"},{"journal-title":"LGBTQ+ Audio Archive Mining Project","year":"0","author":"hanlon","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18352\/lq.10285"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/asi.21327"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.22148\/16.002"},{"journal-title":"Machine Learning + Libraries Summit Event Summary","year":"2020","author":"jakeway","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.acalib.2018.02.001"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3219104.3229290"},{"key":"ref49","first-page":"12","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018"},{"article-title":"Deep speech: Scaling up end-to-end speech recognition","year":"2014","author":"hannun","key":"ref9"},{"key":"ref46","first-page":"163","author":"aggarwal","year":"0","journal-title":"Mining Text Data"},{"article-title":"Text categorisation: A survey","year":"1999","author":"aas","key":"ref45"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1139"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2009.02.037"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1142\/SMPAI"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-016-0924-1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511976247"}],"event":{"name":"2020 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2020,12,10]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2020,12,13]]}},"container-title":["2020 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9377717\/9377728\/09378438.pdf?arnumber=9378438","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T14:37:10Z","timestamp":1698071830000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9378438\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,10]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/bigdata50022.2020.9378438","relation":{},"subject":[],"published":{"date-parts":[[2020,12,10]]}}}