{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T10:30:55Z","timestamp":1769423455404,"version":"3.49.0"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"EPSRC Project","award":["EP\/R012180\/1"],"award-info":[{"award-number":["EP\/R012180\/1"]}]},{"name":"EPSRC Project","award":["EP\/R012180\/1"],"award-info":[{"award-number":["EP\/R012180\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3313417","type":"journal-article","created":{"date-parts":[[2023,9,8]],"date-time":"2023-09-08T17:38:56Z","timestamp":1694194736000},"page":"3346-3361","source":"Crossref","is-referenced-by-count":2,"title":["Phonetic Error Analysis Beyond Phone Error Rate"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8761-021X","authenticated-orcid":false,"given":"Erfan","family":"Loweimi","sequence":"first","affiliation":[{"name":"Depatment of Engineering, King&#x0027;s College London - Strand Campus, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9016-5092","authenticated-orcid":false,"given":"Andrea","family":"Carmantini","sequence":"additional","affiliation":[{"name":"Centre for Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9597-9615","authenticated-orcid":false,"given":"Peter","family":"Bell","sequence":"additional","affiliation":[{"name":"Centre for Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8790-3389","authenticated-orcid":false,"given":"Steve","family":"Renals","sequence":"additional","affiliation":[{"name":"Centre for Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5128-5099","authenticated-orcid":false,"given":"Zoran","family":"Cvetkovic","sequence":"additional","affiliation":[{"name":"Depatment of Engineering, King&#x0027;s College London - Strand Campus, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1072.001.0001","volume-title":"Acoustic Phonetics, Ser. Current Studies in Linguistics Series","author":"Stevens","year":"2000"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495686"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.036"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511627736.017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1994.389337"},{"key":"ref6","first-page":"155","article-title":"Speaker recognition and broad phonetic groups","volume-title":"Proc. SPPRA","author":"Antal","year":"2006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1400"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1994.389258"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICALT.2003.1215049"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SCFT.1993.762326"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596022"},{"key":"ref12","first-page":"14","article-title":"Language identification: Insights from the classification of hand annotated phone transcripts","volume-title":"Proc. Int. Speech. Community Assoc.","author":"Kempton","year":"2008"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2004-322"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-685"},{"key":"ref15","article-title":"The role of phonetic units in speech emotion recognition","author":"Yuan","year":"2021","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885907"},{"key":"ref17","first-page":"1760","article-title":"A hierarchical broad-class classification to enhance phoneme recognition","volume-title":"Proc. IEEE Eur. Signal Process. Conf.","author":"Lopes","year":"2009"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1186\/1687-6180-2012-158"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023180"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-123"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075885"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373547"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77347-4_13"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-302"},{"key":"ref25","first-page":"96","article-title":"Acoustic units selection in Chinese-English bilingual speech recognition","volume-title":"Proc. NOLISP","author":"Yang","year":"2007"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.03.011"},{"key":"ref27","first-page":"475","article-title":"Speech as eyes see it","volume-title":"Attention and Performance VIII","author":"Cole","year":"1980"},{"key":"ref28","article-title":"Speech as eyes see it","author":"Cole","year":"1981"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2010.05.013"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-7687.2011.01089.x"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-linguistics-011718-011919"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.4930"},{"key":"ref33","volume-title":"Probabilistic Machine Learning: An Introduction","author":"Murphy","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1992-277"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115550"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref37","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(94)90039-6"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1998-522"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2010286"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1257"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3104193"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05499-1_5"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.11.003"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854665"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-019-09630-9"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90010-7"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/29.46546"},{"key":"ref53","first-page":"1","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. Workshop Automat. Speech Recognit. Understanding","author":"Povey","year":"2011"},{"key":"ref54","volume-title":"Spoken Language Processing: A Guide to Theory, Algorithm, and System Development","author":"Huang","year":"2001"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/s0095-4470(19)31520-7"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneuroling.2010.02.011"},{"key":"ref57","first-page":"13","volume-title":"Phonetic Universals in Vowel Systems","author":"Lindblom","year":"1986"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/11550907_126"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854049"},{"key":"ref60","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref61","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","volume-title":"Int. Conf. Mach. Learn.","author":"Nair","year":"2010"},{"key":"ref62","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Ioffe","year":"2015"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683713"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref65","first-page":"26","article-title":"Rmsprop: Divide the gradient by a running average of its recent magnitude. Coursera: Neural networks for machine learning","volume":"4","author":"Tieleman","year":"2012","journal-title":"COURSERA Neural Netw. Mach. Learn"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178780"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3237167"},{"key":"ref68","first-page":"28","article-title":"The AMI meeting corpus","volume-title":"Proc. 2nd Int. Conf. Mach. Learn. Multimodal Interact.","author":"Mccowan","year":"2005"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1121\/1.3493450"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1121\/1.401662"},{"key":"ref71","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596119"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref77","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10244118.pdf?arnumber=10244118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T01:50:01Z","timestamp":1705542601000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10244118\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3313417","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}