{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T02:55:58Z","timestamp":1773370558581,"version":"3.50.1"},"reference-count":53,"publisher":"Elsevier BV","issue":"5","license":[{"start":{"date-parts":[[2012,10,1]],"date-time":"2012-10-01T00:00:00Z","timestamp":1349049600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computer Speech & Language"],"published-print":{"date-parts":[[2012,10]]},"DOI":"10.1016\/j.csl.2012.02.003","type":"journal-article","created":{"date-parts":[[2012,3,1]],"date-time":"2012-03-01T09:31:16Z","timestamp":1330594276000},"page":"349-370","source":"Crossref","is-referenced-by-count":6,"title":["A monotonic statistical machine translation approach to speaking style transformation"],"prefix":"10.1016","volume":"26","author":[{"given":"Graham","family":"Neubig","sequence":"first","affiliation":[]},{"given":"Yuya","family":"Akita","sequence":"additional","affiliation":[]},{"given":"Shinsuke","family":"Mori","sequence":"additional","affiliation":[]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.csl.2012.02.003_bib0005","doi-asserted-by":"crossref","first-page":"1539","DOI":"10.1109\/TASL.2009.2037400","article-title":"Statistical transformation of language and pronunciation models for spontaneous speech recognition","volume":"18","author":"Akita","year":"2010","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"10.1016\/j.csl.2012.02.003_bib0010","series-title":"Proceedings of the 10th Annual Conference of the International Speech Communication Association (InterSpeech)","first-page":"84","article-title":"Automatic transcription system for meetings of the Japanese national congress","author":"Akita","year":"2009"},{"issue":"1","key":"10.1016\/j.csl.2012.02.003_bib0015","first-page":"39","article-title":"A method to convert Sana\u2019ani accent to modern standard Arabic","volume":"8","author":"Al-Gaphari","year":"2010","journal-title":"International Journal of Information, Science, and Technology"},{"key":"10.1016\/j.csl.2012.02.003_bib0020","series-title":"Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics","first-page":"40","article-title":"Generalized algorithms for constructing statistical language models","author":"Allauzen","year":"2003"},{"key":"10.1016\/j.csl.2012.02.003_bib0025","series-title":"Proceedings of the CIAA\u201907","first-page":"11","article-title":"OpenFst: a general and efficient weighted finite-state transducer library","author":"Allauzen","year":"2007"},{"key":"10.1016\/j.csl.2012.02.003_bib0030","series-title":"The 6th International Conference on Informatics and Systems (INFOS 2008)","article-title":"A hybrid approach for converting written Egyptian colloquial dialect into diacritized Arabic","author":"Bakr","year":"2008"},{"key":"10.1016\/j.csl.2012.02.003_bib0035","series-title":"Proceedings of the 30th Annual Meeting of the Association for Computational Linguistics","first-page":"56","article-title":"Integrating multiple knowledge sources for detection and correction of repairs in human\u2013computer dialog","author":"Bear","year":"1992"},{"key":"10.1016\/j.csl.2012.02.003_bib0040","first-page":"263","article-title":"The mathematics of statistical machine translation: parameter estimation","volume":"19","author":"Brown","year":"1993","journal-title":"Computational Linguistics"},{"issue":"3","key":"10.1016\/j.csl.2012.02.003_bib0045","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1109\/MSP.2008.917989","article-title":"Recent efforts in spoken language translation","volume":"25","author":"Casacuberta","year":"2008","journal-title":"IEEE Signal Processing Magazine"},{"issue":"2","key":"10.1016\/j.csl.2012.02.003_bib0050","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1162\/089120104323093294","article-title":"Machine translation with inferred stochastic finite-state transducers","volume":"30","author":"Casacuberta","year":"2004","journal-title":"Computational Linguistics"},{"key":"10.1016\/j.csl.2012.02.003_bib0055","series-title":"Proceedings of the Second Meeting of the North American Chapter of the Association for Computational Linguistics","first-page":"9","article-title":"Edit detection and parsing for transcribed speech","author":"Charniak","year":"2001"},{"key":"10.1016\/j.csl.2012.02.003_bib0060","series-title":"Proceedings of the 34th Annual Meeting of the Association for Computational Linguistics","first-page":"310","article-title":"An empirical study of smoothing techniques for language modeling","author":"Chen","year":"1996"},{"key":"10.1016\/j.csl.2012.02.003_bib0065","series-title":"Proceedings of the 11th European Chapter of the Association for Computational Linguistics","article-title":"Parsing Arabic dialects","author":"Chiang","year":"2006"},{"key":"10.1016\/j.csl.2012.02.003_bib0070","series-title":"ISCA Tutorial and Research Workshop (ITRW) on Prosody in Speech Recognition and Understanding","article-title":"Punctuation annotation using statistical prosody models","author":"Christensen","year":"2001"},{"key":"10.1016\/j.csl.2012.02.003_bib0075","first-page":"55","article-title":"Spoken and written language: exploring orality and literacy, chap","author":"Clancy","year":"1982","journal-title":"Written and Spoken Style in Japanese Narratives, ABLEX"},{"key":"10.1016\/j.csl.2012.02.003_bib0080","series-title":"Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","article-title":"Punctuating speech for information extraction","author":"Favre","year":"2008"},{"key":"10.1016\/j.csl.2012.02.003_bib0085","unstructured":"Fitzgerald, E., 2009. Reconstructing Spontaneous Speech. PhD Thesis, Johns Hopkins University."},{"key":"10.1016\/j.csl.2012.02.003_bib0090","series-title":"ASR2000-Automatic Speech Recognition: Challenges for the new Millennium ISCA Tutorial and Research Workshop (ITRW)","article-title":"Sentence boundary detection in broadcast speech transcripts","author":"Gotoh","year":"2000"},{"key":"10.1016\/j.csl.2012.02.003_bib0095","series-title":"Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","first-page":"4741","article-title":"Restoring punctuation and capitalization in transcribed speech","author":"Gravano","year":"2009"},{"key":"10.1016\/j.csl.2012.02.003_bib0100","series-title":"Proceedings of the 8th European Conference on Speech Communication and Technology (EuroSpeech)","first-page":"2781","article-title":"Correction of disfluencies in spontaneous speech using a noisy-channel approach","author":"Honal","year":"2003"},{"key":"10.1016\/j.csl.2012.02.003_bib0105","series-title":"Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 2005","first-page":"969","article-title":"Automatic disfluency removal on recognized spontaneous speech-rapid adaptation to speaker-dependent disfluencies","author":"Honal","year":"2005"},{"key":"10.1016\/j.csl.2012.02.003_bib0110","series-title":"ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition","article-title":"Paraphrasing spontaneous speech using weighted finite-state transducers","author":"Hori","year":"2003"},{"key":"10.1016\/j.csl.2012.02.003_bib0115","series-title":"Proceedings of the 7th International Conference on Speech and Language Processing (ICSLP)","article-title":"Maximum entropy model for punctuation annotation from speech","author":"Huang","year":"2002"},{"key":"10.1016\/j.csl.2012.02.003_bib0120","series-title":"Proceedings of the Rich Transcription Workshop","article-title":"An improved model for recognizing disfluencies in conversational speech","author":"Johnson","year":"2004"},{"key":"10.1016\/j.csl.2012.02.003_bib0125","series-title":"Proceedings of the 8th European Conference on Speech Communication and Technology (EuroSpeech)","first-page":"1585","article-title":"Measuring the readability of automatic speech-to-text transcripts","author":"Jones","year":"2003"},{"key":"10.1016\/j.csl.2012.02.003_bib0130","series-title":"Proceedings of the Human Language Technology Conference\/North American Chapter of the Association for Computational Linguistics Meeting (HLT\/NAACL)","first-page":"137","article-title":"Detecting structural metadata with decision trees and transformation-based learning","author":"Kim","year":"2004"},{"key":"10.1016\/j.csl.2012.02.003_bib0135","series-title":"Proceedings of the 7th European Conference on Speech Communication and Technology (EuroSpeech)","article-title":"The use of prosody in a combined system for punctuation generation and speech recognition","author":"Kim","year":"2001"},{"key":"10.1016\/j.csl.2012.02.003_bib0140","first-page":"181","article-title":"Improved backing-off for M-gram language modeling","volume":"1","author":"Kneser","year":"1995","journal-title":"Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP)"},{"issue":"4","key":"10.1016\/j.csl.2012.02.003_bib0145","first-page":"607","article-title":"Decoding complexity in word-replacement translation models","volume":"25","author":"Knight","year":"1999","journal-title":"Computational Linguistics"},{"key":"10.1016\/j.csl.2012.02.003_bib0150","series-title":"Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics","article-title":"Moses: open source toolkit for statistical machine translation","author":"Koehn","year":"2007"},{"key":"10.1016\/j.csl.2012.02.003_bib0155","first-page":"1","article-title":"Design, creation, and analysis of Czech corpora for structural metadata extraction from speech","author":"Kol\u00e1\u0159","year":"2010","journal-title":"Language Resources and Evaluation"},{"key":"10.1016\/j.csl.2012.02.003_bib0160","series-title":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","article-title":"Recent development of open-source speech recognition engine Julius","author":"Lee","year":"2009"},{"key":"10.1016\/j.csl.2012.02.003_bib0165","series-title":"Proceedings of the 9th International Conference on Spoken Language Processing (InterSpeech 2006 - ICSLP)","first-page":"1978","article-title":"Automatic grammar correction for second-language learners","author":"Lee","year":"2006"},{"issue":"5","key":"10.1016\/j.csl.2012.02.003_bib0170","doi-asserted-by":"crossref","first-page":"1526","DOI":"10.1109\/TASL.2006.878255","article-title":"Enriching speech recognition with automatic detection of sentence boundaries and disfluencies","volume":"14","author":"Liu","year":"2006","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"10.1016\/j.csl.2012.02.003_bib0175","series-title":"Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","first-page":"957","article-title":"Structural metadata research in the EARS program","author":"Liu","year":"2005"},{"key":"10.1016\/j.csl.2012.02.003_bib0180","series-title":"Proceedings of the ISCA\/IEEE Workshop on Spontaneous Speech","article-title":"Corpus of spontaneous Japanese: its design and evaluation","author":"Maekawa","year":"2003"},{"key":"10.1016\/j.csl.2012.02.003_bib0185","series-title":"Proceedings of the 9th International Conference on Spoken Language Processing (InterSpeech 2006 - ICSLP)","first-page":"749","article-title":"A phrase-level machine translation approach for disfluency detection using weighted finite state transducers","author":"Maskey","year":"2006"},{"issue":"2","key":"10.1016\/j.csl.2012.02.003_bib0190","first-page":"269","article-title":"Finite-state transducers in language and speech processing","volume":"23","author":"Mohri","year":"1997","journal-title":"Computational Linguistics"},{"key":"10.1016\/j.csl.2012.02.003_bib0195","series-title":"Proceedings of the 31st Annual Meeting of the Association for Computational Linguistics","first-page":"46","article-title":"A speech-first model for repair detection and correction","author":"Nakatani","year":"1993"},{"key":"10.1016\/j.csl.2012.02.003_bib0200","series-title":"Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics","first-page":"160","article-title":"Minimum error rate training in statistical machine translation","author":"Och","year":"2003"},{"key":"10.1016\/j.csl.2012.02.003_bib0205","series-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","first-page":"295","article-title":"Discriminative training and maximum entropy models for statistical machine translation","author":"Och","year":"2002"},{"key":"10.1016\/j.csl.2012.02.003_bib0210","doi-asserted-by":"crossref","unstructured":"Och, F.J., Ney, H., 2004. The Alignment Template Approach to Statistical Machine Translation, vol. 30. MIT Press, pp. 417\u2013449, ISSN 0891-2017.","DOI":"10.1162\/0891201042544884"},{"key":"10.1016\/j.csl.2012.02.003_bib0215","series-title":"Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","article-title":"Sentence segmentation and punctuation recovery for spoken language translation","author":"Paulik","year":"2008"},{"key":"10.1016\/j.csl.2012.02.003_bib0220","series-title":"Machine Translation Summit XI","first-page":"177","article-title":"Improving spoken language translation by automatic disfluency removal: evidence from conversational speech transcripts","author":"Rao","year":"2007"},{"key":"10.1016\/j.csl.2012.02.003_bib0225","series-title":"Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","first-page":"57","article-title":"Reranking for sentence boundary detection in conversational speech","author":"Roark","year":"2006"},{"key":"10.1016\/j.csl.2012.02.003_bib0230","series-title":"Proceedings of the 20th International Conference on Computational Linguistics","first-page":"1107","article-title":"Dependency structure analysis and sentence boundary detection in spontaneous Japanese","author":"Shitaoka","year":"2004"},{"key":"10.1016\/j.csl.2012.02.003_bib0235","series-title":"Proceedings of the 8th International Conference on Spoken Language Processing (InterSpeech 2004 \u2013 ICSLP)","first-page":"2169","article-title":"Automatic transformation of lecture transcription into document style using statistical framework","author":"Shitaoka","year":"2004"},{"key":"10.1016\/j.csl.2012.02.003_bib0240","unstructured":"Shriberg, E., 1994. Preliminaries to a Theory of Speech Disfluencies. PhD Thesis, University of California at Berkeley."},{"key":"10.1016\/j.csl.2012.02.003_bib0245","series-title":"Proceedings of the 5th European Conference on Speech Communication and Technology (EuroSpeech)","article-title":"A prosody-only decision-tree model for disfluency detection","author":"Shriberg","year":"1997"},{"key":"10.1016\/j.csl.2012.02.003_bib0250","series-title":"Proceedings of the Human Language Technology: The 11th Annual Conference of the North American Chapter of the Association for Computational Linguistics","article-title":"Formatting time-aligned ASR transcripts for readability","author":"Shugrina","year":"2010"},{"key":"10.1016\/j.csl.2012.02.003_bib0255","series-title":"Proceedings of the Human Language Technology Conference\/North American Chapter of the Association for Computational Linguistics Meeting (HLT\/NAACL)","first-page":"157","article-title":"A lexically-driven algorithm for disfluency detection","author":"Snover","year":"2004"},{"issue":"5","key":"10.1016\/j.csl.2012.02.003_bib0260","doi-asserted-by":"crossref","first-page":"1574","DOI":"10.1109\/TASL.2006.878267","article-title":"Edit disfluency detection and correction using a cleanup language model and an alignment model","volume":"14","author":"Yeh","year":"2006","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"10.1016\/j.csl.2012.02.003_bib0265","series-title":"Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","article-title":"Constrained phrase-based translation using weighted finite-state transducers","author":"Zhou","year":"2005"}],"container-title":["Computer Speech & Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230812000149?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230812000149?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,6,24]],"date-time":"2019-06-24T19:09:02Z","timestamp":1561403342000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0885230812000149"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,10]]},"references-count":53,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2012,10]]}},"alternative-id":["S0885230812000149"],"URL":"https:\/\/doi.org\/10.1016\/j.csl.2012.02.003","relation":{},"ISSN":["0885-2308"],"issn-type":[{"value":"0885-2308","type":"print"}],"subject":[],"published":{"date-parts":[[2012,10]]}}}