{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:35:52Z","timestamp":1774020952023,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/icassp.2017.7953078","type":"proceedings-article","created":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T21:35:36Z","timestamp":1497994536000},"page":"4850-4854","source":"Crossref","is-referenced-by-count":5,"title":["Confidence measures for CTC-based phone synchronous decoding"],"prefix":"10.1109","author":[{"given":"Zhehuai","family":"Chen","sequence":"first","affiliation":[]},{"given":"Yimeng","family":"Zhuang","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862067"},{"key":"ref11","first-page":"i","article-title":"Maximum entropy based normalization of word posteriors for phonetic and lvc-sr lattice search","volume":"1","author":"yu","year":"2006","journal-title":"2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref13","article-title":"Phoneme recognition in timit with blstm-ctc","author":"fern\u00e1ndez","year":"2008","journal-title":"ar Xiv preprint arXiv 0804 3269"},{"key":"ref14","first-page":"604","article-title":"Acoustic modelling with cd-ctc-smbr lstm rnns","author":"sainath","year":"2015","journal-title":"IEEE 2015 Automatic Speech Recognition and Understanding Workshop (ASRU)"},{"key":"ref15","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2015","journal-title":"ar Xiv preprint arX-iv 1512 02167"},{"key":"ref16","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"sak","year":"2015","journal-title":"ar Xiv preprint arX-iv 1507 06947"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472152"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472820"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1999.0126"},{"key":"ref4","article-title":"Fusing multiple confidence measures for chinese spoken term detection","author":"ma","year":"2011","journal-title":"Twelfth Annual Conference of the InternationalSpeech Communication Association"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1999-320","article-title":"Efficient general lattice generation and rescoring","author":"ljolje","year":"1999","journal-title":"Sixth European Conference on Speech Communication and Technology"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1886","DOI":"10.21437\/Interspeech.2013-458","article-title":"A new dnn-based high quality pronunciation evaluation for computer-aided language learning (call)","author":"hu","year":"2013","journal-title":"InterSpeech"},{"key":"ref6","year":"2013","journal-title":"mathew Stephen Seigel Confidence Estimation for Automatic Speech Recognition Hypotheses"},{"key":"ref29","article-title":"Sclite scoring package version 1.5","author":"fiscus","year":"1998","journal-title":"US National Institute of Standards and Technology (NIST)"},{"key":"ref5","article-title":"Acoustic and word lattice based algorithms for confidence scores","author":"falavigna","year":"2002","journal-title":"InterSpeech"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1994.389728"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2141988"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.12.004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/89.906002"},{"key":"ref1","article-title":"Speech is 3x faster than typing for english and mandarin text entry on mobile devices","author":"ruan","year":"2016","journal-title":"ar Xiv preprint arXiv 1608 07323"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-831"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288848"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2625459"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2005.07.005"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2234115"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1994.389562"},{"key":"ref25","article-title":"Frame based system combination and a comparison with weighted rover and cnc","author":"hoffmeister","year":"2006","journal-title":"INTERSPEECH Citeseer"}],"event":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"New Orleans, LA","start":{"date-parts":[[2017,3,5]]},"end":{"date-parts":[[2017,3,9]]}},"container-title":["2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7943262\/7951776\/07953078.pdf?arnumber=7953078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T20:57:14Z","timestamp":1750366634000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7953078\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp.2017.7953078","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}