{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T14:48:06Z","timestamp":1773326886622,"version":"3.50.1"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3219838","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T21:24:11Z","timestamp":1667597051000},"page":"117053-117066","source":"Crossref","is-referenced-by-count":1,"title":["Automatic Speech Recognition Post-Processing for Readability: Task, Dataset and a Two-Stage Pre-Trained Approach"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7321-7583","authenticated-orcid":false,"given":"Junwei","family":"Liao","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Shi","sequence":"additional","affiliation":[{"name":"Microsoft Cognitive Services Research Group, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[{"name":"Westone Information Industry Inc., Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.3115\/1220355.1220427"},{"key":"ref72","first-page":"190","article-title":"Machine translation evaluation: N-grams to the rescue","author":"papineni","year":"2002","journal-title":"Proc LREC"},{"key":"ref71","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref70","article-title":"Sequence-to-sequence pre-training with data augmentation for sentence rewriting","author":"zhang","year":"2019","journal-title":"arXiv 1909 06002"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-65"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324914000175"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414912"},{"key":"ref39","first-page":"110","article-title":"The RT04 evaluation structural metadata systems at cued","author":"tomalin","year":"2004","journal-title":"Proc Fall Rich Transcription Workshop (RT-04)"},{"key":"ref75","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume":"2015","author":"kingma","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent (ICLR)"},{"key":"ref38","first-page":"1","article-title":"The ICSI\/SRI\/UW RT-04 structural metadata extraction system","author":"liu","year":"2004","journal-title":"Proc EARS RT-04 Workshop"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref79","doi-asserted-by":"crossref","first-page":"338","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","journal-title":"Proc INTERSPEECH"},{"key":"ref33","first-page":"3529","article-title":"Semi-supervised disfluency detection","author":"wang","year":"2018","journal-title":"Proc 27th Int Conf Comput Linguistics"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1132"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4423"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00282"},{"key":"ref37","article-title":"Effective, affordable, reusable speech-to-text (ears)","author":"wayne","year":"2003"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1416464"},{"key":"ref35","first-page":"198","article-title":"Formatting time-aligned ASR transcripts for readability","author":"shugrina","year":"2010","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref34","first-page":"2756","article-title":"Neural constituency parsing of speech transcripts","volume":"1","author":"lou","year":"2019","journal-title":"Proc 2019 Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054387"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0182"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472084"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-911"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1007\/978-3-642-32790-2_54","article-title":"Discretion of speech units for the text post-processing phase of automatic transcription (in the Czech language)","author":"\u0161kodov\u00e1","year":"2012","journal-title":"Proc of the 9th International Conf on Text Speech and Dialogue"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4406"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960690"},{"key":"ref65","first-page":"180","article-title":"A new dataset and method for automatically grading Esol texts","author":"yannakoudakis","year":"2011","journal-title":"Proc ACL"},{"key":"ref66","first-page":"147","article-title":"Mining revision log of language learning SNS for automated Japanese error correction of second language learners","author":"mizumoto","year":"2011","journal-title":"Proc IJCNLP"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.89"},{"key":"ref67","first-page":"1","article-title":"Tense and aspect error correction for ESL learners using global context","author":"tajiri","year":"2012","journal-title":"Proc ACL"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.4324\/9781315841342-1"},{"key":"ref69","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCS48705.2020.9074180"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461870"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.03.005"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053051"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683745"},{"key":"ref24","first-page":"252","article-title":"Segmentation and punctuation prediction in speech language translation using a monolingual translation system","author":"cho","year":"2012","journal-title":"Proc Int Workshop Spoken Lang Transl (IWSLT)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518807"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.05.008"},{"key":"ref25","first-page":"1","article-title":"Punctuation insertion for real-time spoken language translation","author":"cho","year":"2015","journal-title":"Proc 12th Int Workshop Spoken Lang Transl Papers"},{"key":"ref50","author":"radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref51","volume":"1","author":"radford","year":"2019","journal-title":"Language Models are Unsupervised Multitask Learners"},{"key":"ref59","article-title":"Modeling multi-speaker latent space to improve neural TTS: Quick enrolling new speaker and enhancing premium voice","author":"deng","year":"2018","journal-title":"arXiv 1812 05253"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref57","article-title":"Reaching human-level performance in automatic grammatical error correction: An empirical study","author":"ge","year":"2018","journal-title":"arXiv 1807 01270"},{"key":"ref56","first-page":"927","article-title":"Switchboard-1 release 2","volume":"926","author":"godfrey","year":"1997","journal-title":"Linguistic Data Consortium"},{"key":"ref55","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"raffel","year":"2019","journal-title":"arXiv 1910 10683"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref53","first-page":"5926","article-title":"MASS: Masked sequence to sequence pre-training for language generation","volume":"97","author":"song","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn (ICML)"},{"key":"ref52","first-page":"5754","article-title":"XlNet: Generalized autoregressive pretraining for language understanding","volume":"32","author":"yang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462492"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.918411"},{"key":"ref40","first-page":"64","article-title":"Comparing and combining generative and posterior probability models: Some advances in sentence boundary detection in speech","author":"liu","year":"2004","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28577-7_12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2010.2089620"},{"key":"ref14","article-title":"RT-03 MDE training data speech","author":"strassel","year":"2004","journal-title":"Linguistic Data Consortium"},{"key":"ref15","author":"strassel","year":"2003","journal-title":"Simple Metadata Annotation Specification Version 5 0"},{"key":"ref82","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"arXiv 1211 3711"},{"key":"ref16","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"2019","journal-title":"arXiv 1907 11692"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref17","first-page":"13063","article-title":"Unified language model pre-training for natural language understanding and generation","author":"dong","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref84","first-page":"577","article-title":"Attention-based models for speech recognition","volume":"28","author":"chorowski","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst"},{"key":"ref18","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414626"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-srw.10"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-3514-7_1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref5","first-page":"109","article-title":"Automated generation of meeting minutes using deep learning techniques","volume":"2021","author":"manuel","year":"2021","journal-title":"Int J Comput Digit Syst"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472641"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.61"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-233"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534401"},{"key":"ref49","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.9"},{"key":"ref46","article-title":"Using DeepSpeed and megatron to train megatron-turing NLG 530B, a large-scale generative language model","author":"smith","year":"2022","journal-title":"arXiv 2201 11990"},{"key":"ref45","author":"lieber","year":"2021","journal-title":"Jurassic-1 Technical details and evaluation"},{"key":"ref48","article-title":"Palm: Scaling language modeling with pathways","author":"chowdhery","year":"2022","journal-title":"arXiv 2204 02311"},{"key":"ref47","article-title":"Scaling language models: Methods, analysis & insights from training gopher","author":"rae","year":"2021","journal-title":"arXiv 2112 11446"},{"key":"ref42","first-page":"6294","article-title":"Learned in translation: Contextualized word vectors","volume":"30","author":"mccann","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst"},{"key":"ref41","first-page":"3079","article-title":"Semi-supervised sequence learning","volume":"28","author":"dai","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst"},{"key":"ref44","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"brown","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09940272.pdf?arnumber=9940272","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T08:59:49Z","timestamp":1728291589000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9940272\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3219838","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}