{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:14:05Z","timestamp":1740172445907,"version":"3.37.3"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Research Grants Council GRF","award":["14227216"],"award-info":[{"award-number":["14227216"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/taslp.2019.2937953","type":"journal-article","created":{"date-parts":[[2019,8,28]],"date-time":"2019-08-28T20:07:54Z","timestamp":1567022874000},"page":"2000-2011","source":"Crossref","is-referenced-by-count":7,"title":["Exploiting Cross-Lingual Speaker and Phonetic Diversity for Unsupervised Subword Modeling"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2531-8480","authenticated-orcid":false,"given":"Siyuan","family":"Feng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tan","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1476"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2387382"},{"key":"ref33","first-page":"3989","article-title":"Unsupervised optimal phoneme segmentation: Objectives, algorithm and comparisons","author":"qiao","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269014"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461648"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764270"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319337"},{"key":"ref36","first-page":"501","article-title":"A segment model based approach to speech recognition","author":"lee","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659619"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2016.7918442"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref27","first-page":"3199","article-title":"A comparison of neural network methods for unsupervised representation learning on the zero resource speech challenge","author":"renshaw","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269010"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-405"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269011"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846245"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68456-7_14"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2852500"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-988"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_5"},{"key":"ref50","first-page":"1","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Autom Speech Recognit Understanding Workshop"},{"key":"ref51","first-page":"901","article-title":"SRILM – an extensible language modeling toolkit","author":"stolcke","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1990.2.4.490"},{"key":"ref53","first-page":"2059","article-title":"SpeechDat-E: Five eastern european speech databases for voice-operated teleservices completed","author":"van den heuvel","year":"0","journal-title":"Proc INTERSPEECH"},{"article-title":"Phoneme recognition based on long temporal context","year":"2009","author":"schwarz","key":"ref52"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-313"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953237"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2517567"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269009"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1081"},{"key":"ref15","article-title":"Weakly supervised multi-embeddings learning of acoustic models","author":"synnaeve","year":"2014","journal-title":"arXiv 1412 6645"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179087"},{"article-title":"Multilingual and unsupervised subword modeling for zero-resource languages","year":"2018","author":"hermann","key":"ref17"},{"key":"ref18","first-page":"620","article-title":"Parallel sampling of DP mixture models using sub-cluster splits","author":"chang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","first-page":"3189","article-title":"Parallel inference of Dirichlet process Gaussian mixture models for unsupervised acoustic modeling: A feasibility study","author":"chen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-371"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268953"},{"key":"ref5","first-page":"747","article-title":"Composite embedding systems for zerospeech 2017 track 1","author":"shibata","year":"0","journal-title":"Proc IEEE Autom Speech Recognit Understanding Workshop"},{"key":"ref8","first-page":"678","article-title":"Fully unsupervised small-vocabulary speech recognition using a segmental Bayesian model","author":"kamper","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPA.2012.6310546"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00101-1"},{"key":"ref9","first-page":"3169","article-title":"The zero resource speech challenge 2015","author":"versteegh","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref45","first-page":"338","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472622"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424230"},{"journal-title":"A Manual of Phonology","year":"1955","author":"hockett","key":"ref42"},{"journal-title":"Economie des Changements Phonétiques","year":"1970","author":"martinet","key":"ref41"},{"key":"ref44","first-page":"2947","article-title":"Investigation into bottle-neck features for meeting speech recognition","author":"gr\u00e9zl","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.032"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8817316\/08818297.pdf?arnumber=8818297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:54:27Z","timestamp":1657745667000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8818297\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":54,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2937953","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2019,12]]}}}