{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T16:45:14Z","timestamp":1762101914886,"version":"3.37.3"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2016,12,1]],"date-time":"2016-12-01T00:00:00Z","timestamp":1480550400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001691","name":"JSPS KAKENHI","doi-asserted-by":"publisher","award":["26280063"],"award-info":[{"award-number":["26280063"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/taslp.2016.2603599","type":"journal-article","created":{"date-parts":[[2016,8,26]],"date-time":"2016-08-26T18:45:03Z","timestamp":1472237103000},"page":"2400-2413","source":"Crossref","is-referenced-by-count":8,"title":["Estimating Speech Recognition Accuracy Based on Error Type Classification"],"prefix":"10.1109","volume":"24","author":[{"given":"Atsunori","family":"Ogawa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takaaki","family":"Hori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsushi","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"849","article-title":"Statistical methods for comparing pattern recognition algorithms and comments on evaluating speech recognition performance","volume":"50","author":"nakagawa","year":"1994","journal-title":"J Acoust Soc Jpn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857791"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495106"},{"key":"ref30","first-page":"135","article-title":"Benchmark test for speech recognition using the corpus of spontaneous Japanese","author":"kawahara","year":"0","journal-title":"Proc Workshop Spontaneous Speech Process Recognit"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178796"},{"key":"ref35","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref34","first-page":"3581","article-title":"A general artificial neural network extension for HTK","author":"zhang","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"year":"2015","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424207"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.12.004"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367036"},{"key":"ref15","first-page":"4085","article-title":"Confidence estimation, OOV detection, and language ID using phone-to-word transcription and phone-level alignments","author":"white","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref16","first-page":"1942","article-title":"CRF-based combination of contextual features to improve a posteriori word-level confidence measures","author":"fayolle","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2141988"},{"article-title":"Confidence estimation for automatic speech recognition hypotheses","year":"2013","author":"seigel","key":"ref18"},{"key":"ref19","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960625"},{"key":"ref4","first-page":"-865i","article-title":"Investigations into the relationship between measurable speech quality and speech recognition rate for telephony speech","author":"sun","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref27","first-page":"2553","article-title":"Recent progress in the MIT spoken lecture processing project","author":"glass","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref3","first-page":"2242","article-title":"Predicting the degradation of speech recognition performance from sub-band dynamic ranges","volume":"43","author":"kondo","year":"2002","journal-title":"J Inf Process Soc Jpn"},{"key":"ref6","first-page":"2042","article-title":"Performance estimation of noisy speech recognition considering task complexity","author":"yamada","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref29","first-page":"7","article-title":"Corpus of spontaneous Japanese: Its design and evaluation","author":"maekawa","year":"0","journal-title":"Proc Workshop Spontaneous Speech Process Recognit"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.883254"},{"journal-title":"Speech recognition scoring toolkit (SCTK) version 2 4 0","year":"2009","key":"ref8"},{"key":"ref7","first-page":"562","article-title":"Performance estimation of reverberant speech recognition based on reverberant criteria RSR- ${D}_n$ with acoustic parameters","author":"fukumori","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3650-5"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-5779-3","author":"yu","year":"2015","journal-title":"Automatic Speech Recognition?A Deep Learning Approach"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1561\/2200000013"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148183"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.04.004"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854010"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2000.0152"},{"journal-title":"CRF++0 58","year":"2013","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.889790"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7571201\/07553582.pdf?arnumber=7553582","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T21:31:22Z","timestamp":1692480682000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7553582\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":36,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2603599","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2016,12]]}}}