{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:26:44Z","timestamp":1740122804444,"version":"3.37.3"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2017,6,8]],"date-time":"2017-06-08T00:00:00Z","timestamp":1496880000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2017,10]]},"DOI":"10.1007\/s11042-017-4714-x","type":"journal-article","created":{"date-parts":[[2017,6,8]],"date-time":"2017-06-08T21:07:36Z","timestamp":1496956056000},"page":"20359-20376","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Improving speech transcription by exploiting user feedback and word repetition"],"prefix":"10.1007","volume":"76","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4226-3250","authenticated-orcid":false,"given":"Xiangdong","family":"Wang","sequence":"first","affiliation":[]},{"given":"Ying","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Hong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yueliang","family":"Qian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,6,8]]},"reference":[{"key":"4714_CR1","doi-asserted-by":"crossref","unstructured":"Chen H, Cooper M, Joshi D, Girod B (2014) Multi-modal language models for lecture video retrieval. ACM International Conference on Multimedia, pp 1081\u20131084","DOI":"10.1145\/2647868.2654964"},{"key":"4714_CR2","first-page":"146","volume":"2014","author":"B Favre","year":"2014","unstructured":"Favre B, Rouvier M, Bechet F (2014) Reranked aligners for interactive transcript correction. Proc ICASSP 2014:146\u2013150","journal-title":"Proc ICASSP"},{"key":"4714_CR3","first-page":"949","volume":"2014","author":"D Harwath","year":"2014","unstructured":"Harwath D, Gruenstein A, Mcgraw I et al (2014) Choosing useful word alternates for automatic speech recognition correction interfaces. Proc INTERSPEECH 2014:949\u2013953","journal-title":"Proc INTERSPEECH"},{"key":"4714_CR4","doi-asserted-by":"crossref","unstructured":"Jia D, Wang X, Ma Y, Yang Y, Liu H, Qian Y (2016) Language model adaptation based on correction information for interactive speech transcription. The 2016 International Conference on Progress in Informatics and Computing (PIC-2016), Shanghai","DOI":"10.1109\/PIC.2016.7949506"},{"key":"4714_CR5","doi-asserted-by":"crossref","unstructured":"Karat CM, Halverson C, Horn D, Karat J (1999) Patterns of entry and correction in large vocabulary continuous speech recognition systems. Proc. CHI, pp 568\u2013575","DOI":"10.1145\/302979.303160"},{"key":"4714_CR6","first-page":"4884","volume":"2011","author":"A Laurent","year":"2011","unstructured":"Laurent A, Meignier S et al (2011) Computer-assisted transcription of speech based on confusion network reordering. ICASSP 2011:4884\u20134887","journal-title":"ICASSP"},{"key":"4714_CR7","doi-asserted-by":"crossref","unstructured":"Lecouteux B, Linares G et al (2006) Imperfect transcript driven speech recognition. Interspeech 2006, Pittburgh","DOI":"10.21437\/Interspeech.2006-454"},{"key":"4714_CR8","unstructured":"Li X, Wang X, Qian Y, Lin S (2009) Candidate generation for interactive Chinese speech recognition. Proc. joint conferences on pervasive computing (JCPC), pp 583\u2013588"},{"key":"4714_CR9","doi-asserted-by":"crossref","unstructured":"Liang Y, Iwano K, Shinoda K (2014, Dec 7) An Efficient error correction Interface for speech recognition on mobile touchscreen devices. Proc. Spoken Language Technology (SLT) Workshop, pp 454\u2013459","DOI":"10.1109\/SLT.2014.7078617"},{"key":"4714_CR10","doi-asserted-by":"crossref","unstructured":"Liang Y, Iwano K, Shinoda K (2014, Sept 16) Simple gesture-based error correction Interface for smartphone speech recognition. Proc. INTERSPEECH, pp 1194\u20131198","DOI":"10.21437\/Interspeech.2014-302"},{"issue":"4","key":"4714_CR11","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1006\/csla.2000.0152","volume":"14","author":"L Mangu","year":"2000","unstructured":"Mangu L, Brill E, Stolcke A (2000) Finding consensus in speech recognition: word error minization and other application of confusion network. Comput Speech Lang 14(4):373\u2013400","journal-title":"Comput Speech Lang"},{"key":"4714_CR12","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.specom.2015.09.006","volume":"2015","author":"JDV Miro","year":"2015","unstructured":"Miro JDV, Silvestrecerda JA, Civera J, Turro C, Juan A (2015) Efficiency and usability study of innovative computer-aided transcription strategies for video lecture repositories. Speech Comm 2015:65\u201375","journal-title":"Speech Comm"},{"issue":"2","key":"4714_CR13","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1109\/TMM.2012.2229971","volume":"15","author":"L Nie","year":"2013","unstructured":"Nie L, Wang M, Gao Y, Zha Z-J, Chua T-S (2013) Beyond text QA: multimedia answer generation by harvesting web information. IEEE Trans Multimedia 15(2):426\u2013441","journal-title":"IEEE Trans Multimedia"},{"key":"4714_CR14","doi-asserted-by":"crossref","unstructured":"Ogata J, Goto M (2005) Speech repair: quick error correction just by using selection operation for speech input interfaces. In: Proc Interspeech, pp 133\u2013136, 2006","DOI":"10.21437\/Interspeech.2005-86"},{"key":"4714_CR15","doi-asserted-by":"crossref","first-page":"1269","DOI":"10.21437\/Interspeech.2010-399","volume":"2010","author":"C Parada","year":"2010","unstructured":"Parada C, Sethy A, Dredze M, Jelinek F (2010) A spoken term detection framework for recovering out-of-vocabulary words using the web. Proc INTERSPEECH 2010:1269\u20131272","journal-title":"Proc INTERSPEECH"},{"key":"4714_CR16","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1007\/978-3-540-72847-4_32","volume":"4477","author":"L Rodr\u00edguez","year":"2007","unstructured":"Rodr\u00edguez L, Casacuberta F, Vidal E (2007) Computer assisted transcription of speech. Lect Notes Comput Sci 4477:241\u2013248","journal-title":"Lect Notes Comput Sci"},{"key":"4714_CR17","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez L, Garc\u00eda-Varea I, Vidal E (2010) Multi-modal computer assisted speech transcription. International Conference on Multimodal Interfaces and the Workshop on Machine Learning for Multimodal interaction (ICMI-MLMI '10)","DOI":"10.1145\/1891903.1891943"},{"key":"4714_CR18","unstructured":"Sperber M, Neubig G, Nakamura S, Waibe A (2016) Optimizing computer-assisted transcription quality with iterative user interfaces. Proc. Language Resources and Evaluation (LREC)"},{"key":"4714_CR19","doi-asserted-by":"crossref","unstructured":"Suhm B (1997) Empirical evaluation of interactive Multimodal error correction. Proc. IEEE Workshop on speech recognition and understanding, pp 583\u2013590","DOI":"10.1109\/ASRU.1997.659139"},{"key":"4714_CR20","unstructured":"Suhm B, Myers B, Waibel A (1996) Designing interactive error recovery methods for speech interfaces. Proceedings of ACM CHI. Workshop on Designing the User interface for Speech Recognition applications"},{"issue":"1","key":"4714_CR21","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1080\/02680513.2014.909722","volume":"29","author":"JD Valor Mir\u00f3","year":"2014","unstructured":"Valor Mir\u00f3 JD, Spencer RN, P\u00e9rez Gonz\u00e1lez de Martos A, Garc\u00e9s G, D\u00edaz-Mun\u00edo CT, Civera J, Juan A (2014) Evaluating intelligent interfaces for post-editing automatic transcriptions of online video lectures. Open Learning: The Journal of Open and Distance Learning 29(1):72\u201385","journal-title":"Open Learning: The Journal of Open and Distance Learning"},{"key":"4714_CR22","doi-asserted-by":"crossref","unstructured":"Valor Mir\u00f3 JD, Silvestre-Cerd\u00e0 JA, Civera J, Turr\u00f3 C, Juan A (2015) Efficient generation of high-quality multilingual subtitles for video lecture repositories. In: Conole G, Klobu\u010dar T, Rensing C, Konert J, Lavou\u00e9 \u00c9 (eds) Design for teaching and learning in a networked world. Lecture notes in Computer Science, vol 9307. Springer, Cham","DOI":"10.1007\/978-3-319-24258-3_44"},{"key":"4714_CR23","doi-asserted-by":"crossref","unstructured":"Wang L, Hu T, Liu P, Soong FK (2008) Efficient handwriting correction of speech recognition errors with template constrained posterior (TCP). Proc. INTERSPEECH, pp 2659\u20132662","DOI":"10.21437\/Interspeech.2008-659"},{"issue":"2","key":"4714_CR24","doi-asserted-by":"crossref","first-page":"153","DOI":"10.12720\/joace.4.2.153-158","volume":"4","author":"X Wang","year":"2016","unstructured":"Wang X, Li X, Qian Y, Liu H (2016) Automatic error correction for repeated words in Mandarin speech recognition. Journal of Automation and Control Engineering 4(2):153\u2013158","journal-title":"Journal of Automation and Control Engineering"},{"key":"4714_CR25","unstructured":"Xue J and Zhao Y-X (2005) Improved confusion network algorithm and shortest path search from word lattice. ICASSP 2005; 1: 853\u2013856"},{"key":"4714_CR26","doi-asserted-by":"crossref","unstructured":"Zhang H, Wang X, Qian Y, Lin S (2011) An interactive way to acquire internet documents for language model adaptation of speech recognition systems. International Conference on Intelligent Human-Machine ystems and Cybernetics (IHMSC 2011), pp 97\u2013100","DOI":"10.1109\/IHMSC.2011.29"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-017-4714-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-4714-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-4714-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,29]],"date-time":"2022-07-29T10:10:26Z","timestamp":1659089426000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-017-4714-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6,8]]},"references-count":26,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2017,10]]}},"alternative-id":["4714"],"URL":"https:\/\/doi.org\/10.1007\/s11042-017-4714-x","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2017,6,8]]}}}