{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:29:55Z","timestamp":1742941795562,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319218335"},{"type":"electronic","value":"9783319218342"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-21834-2_7","type":"book-chapter","created":{"date-parts":[[2016,4,20]],"date-time":"2016-04-20T15:06:28Z","timestamp":1461164788000},"page":"71-82","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Investigating Critical Speech Recognition Errors in Spoken Short Messages"],"prefix":"10.1007","author":[{"given":"Aasish","family":"Pappu","sequence":"first","affiliation":[]},{"given":"Teruhisa","family":"Misu","sequence":"additional","affiliation":[]},{"given":"Rakesh","family":"Gupta","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,4,21]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Bacchiani M, Hirschberg J, Rosenberg A, Whittaker S, Hindle D, Isenhour P, Jones M, Stark L, Zamchick G (2001) Scanmail: audio navigation in the voicemail domain. In: Proceedings of the first international conference on human language technology research. Association for Computational Linguistics, pp 1\u20133","DOI":"10.3115\/1072133.1072216"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Bechet F, Favre B (2013) Asr error segment localization for spoken recovery strategy. In: IEEE international conference in acoustics, speech and signal processing (ICASSP), Vancouver (Canada)","DOI":"10.1109\/ICASSP.2013.6638986"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Bohus D, Rudnicky A (2002) Integrating multiple knowledge sources for utterance-level confidence annotation in the cmu communicator spoken dialog system. Technical report, DTIC Document","DOI":"10.21236\/ADA461099"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Burget L, Schwarz P, Matejka P, Hannemann M, Rastrow A, White C, Khudanpur S, Hermansky H, Cernocky J (2008) Combination of strongly and weakly constrained recognizers for reliable detection of oovs. In: IEEE international conference on acoustics, speech and signal processing, ICASSP 2008. IEEE, pp 4081\u20134084","DOI":"10.1109\/ICASSP.2008.4518551"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Burke M, Amento B, Isenhour P (2006) Error correction of voicemail transcripts in scanmail. In: Proceedings of the SIGCHI conference on human factors in computing systems. ACM, pp 339\u2013348","DOI":"10.1145\/1124772.1124823"},{"key":"7_CR6","unstructured":"Gishri M, Silber-Varod V, Moyal A (2010) Lexicon design for transcription of spontaneous voice messages. In: LREC"},{"issue":"3","key":"7_CR7","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/j.specom.2009.10.001","volume":"52","author":"S Goldwater","year":"2010","unstructured":"Goldwater S, Jurafsky D, Manning CD (2010) Which words are hard to recognize? Prosodic, lexical, and disfluency factors that increase speech recognition error rates. Speech Commun 52(3):181\u2013200","journal-title":"Speech Commun"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Huggins-Daines D, Rudnicky AI (2008) Interactive asr error correction for touchscreen devices. In: Proceedings of the 46th annual meeting of the association for computational linguistics on human language technologies: demo session. Association for Computational Linguistics, pp 17\u201319","DOI":"10.3115\/1564144.1564149"},{"key":"7_CR9","unstructured":"Ku T crfpp.sourceforge.net"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Och FJ (2003) Minimum error rate training in statistical machine translation. In: Proceedings of the 41st annual meeting on association for computational linguistics, vol 1. Association for Computational Linguistics, pp 160\u2013167","DOI":"10.3115\/1075096.1075117"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Ogawa A, Hori T, Nakamura A (2012) Recognition rate estimation based on word alignment network and discriminative error type classification. In: 2012 IEEE spoken language technology workshop (SLT). IEEE, pp 113\u2013118","DOI":"10.1109\/SLT.2012.6424207"},{"key":"7_CR12","unstructured":"OpenNLP http:\/\/opennlp.apache.org\/"},{"key":"7_CR13","unstructured":"Owoputi O, OConnor B, Dyer C, Gimpel K, Schneider N, Smith NA (2013) Improved part-of-speech tagging for online conversational text with word clusters. In: Proceedings of NAACL-HLT, pp 380\u2013390"},{"key":"7_CR14","unstructured":"Pincus E, Stoyanchev S, Hirschberg J (2013) Exploring features for localized detection of speech recognition errors. In: Proceedings of the SIGDIAL 2013 conference. Association for Computational Linguistics, pp 132\u2013136"},{"key":"7_CR15","unstructured":"Placeway P, Chen S, Eskenazi M, Jain U, Parikh V, Raj B, Ravishankar M, Rosenfeld R, Seymore K, Siegler M, Stern R, Thayer E (1997) The 1996 Hub-4 Sphinx-3 system. In: Proceedings of DARPA speech recognition workshop, pp 85\u201389"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Qin L, Rudnicky AI (2012) OOV word detection using hybrid models with mixed types of fragments. Interspeech-2012","DOI":"10.21437\/Interspeech.2012-641"},{"key":"7_CR17","first-page":"901","volume":"3","author":"A Stolcke","year":"2002","unstructured":"Stolcke A (2002) SRILM-an extensible language modeling toolkit. System 3:901\u2013904","journal-title":"System"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Whittaker S, Hirschberg J, Nakatani CH (1998) All talk and all action: strategies for managing voicemail messages. In: CHI 98 cconference summary on human factors in computing systems. ACM, pp 249\u2013250","DOI":"10.1145\/286498.286732"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Zhang R, Rudnicky AI (2001) Word level confidence annotation using combinations of features","DOI":"10.21437\/Eurospeech.2001-496"}],"container-title":["Signals and Communication Technology","Situated Dialog in Speech-Based Human-Computer Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-21834-2_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,15]],"date-time":"2023-02-15T19:48:40Z","timestamp":1676490520000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-21834-2_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319218335","9783319218342"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-21834-2_7","relation":{},"ISSN":["1860-4862","1860-4870"],"issn-type":[{"type":"print","value":"1860-4862"},{"type":"electronic","value":"1860-4870"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"21 April 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}