{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T15:40:02Z","timestamp":1750174802860,"version":"3.41.0"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,11]]},"DOI":"10.1109\/ialp.2016.7875947","type":"proceedings-article","created":{"date-parts":[[2017,3,22]],"date-time":"2017-03-22T03:35:46Z","timestamp":1490153746000},"page":"112-115","source":"Crossref","is-referenced-by-count":1,"title":["Speech recognition of under-resourced languages using mismatched transcriptions"],"prefix":"10.1109","author":[{"given":"Van Hai","family":"Do","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nancy F.","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boon Pang","family":"Lim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Hasegawa-Johnson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2208663"},{"key":"ref11","first-page":"6","article-title":"Kernel Density-based Acoustic Model with Cross-lingual Bottleneck Features for Resource Limited LVCSR","author":"do","year":"2014","journal-title":"Proc Inter-speech"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v29i1.9343","article-title":"Acquiring speech transcriptions using mismatched crowdsourcing","author":"jyothi","year":"2015","journal-title":"Proc AAAI"},{"key":"ref13","first-page":"2774","article-title":"Transcribing continuous speech using mismatched crowdsourcing","author":"jyothi","year":"2015","journal-title":"Proc Inter-speech"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472797"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-655"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-736"},{"key":"ref17","article-title":"Mis-matched crowdsourcing based language perception for under-resourced languages","author":"chen","year":"2016","journal-title":"Proc SLTU"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"dempster","year":"1977","journal-title":"Journal of the Royal Statistical Society Series B"},{"year":"0","key":"ref19","article-title":"Carmel finite-state toolkit"},{"key":"ref4","article-title":"A Comparative Study of BNF and DNN Multilingual Training on Cross-lingual Low-resource Speech Recognition","author":"xu","year":"2015","journal-title":"Proc In-terspeech"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495646"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289010"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660022"},{"key":"ref8","first-page":"500","article-title":"Context-dependent phone mapping for LVCSR of under-resourced languages","author":"do","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"2715","DOI":"10.21437\/Interspeech.2008-673","article-title":"Context Sensitive Probabilistic Phone Mapping Model for Cross-lingual Speech Recognition","author":"sim","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947479"},{"key":"ref1","first-page":"2721","article-title":"Experiments On Cross-Language Acoustic Modeling","author":"schultz","year":"2001","journal-title":"Proc ICSLP"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E97.D.285"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-76336-9_3"},{"key":"ref22","article-title":"Vocal tract length perturbation (VTLP) improves speech recognition","author":"jaitly","year":"2013","journal-title":"Proc ICML Workshop on Deep Learning for Audio Speech and Language Processing"},{"key":"ref21","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref23","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Proc Inter-speech"}],"event":{"name":"2016 International Conference on Asian Language Processing (IALP)","start":{"date-parts":[[2016,11,21]]},"location":"Tainan, Taiwan","end":{"date-parts":[[2016,11,23]]}},"container-title":["2016 International Conference on Asian Language Processing (IALP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7871260\/7875919\/07875947.pdf?arnumber=7875947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T15:24:52Z","timestamp":1750173892000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7875947\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/ialp.2016.7875947","relation":{},"subject":[],"published":{"date-parts":[[2016,11]]}}}