{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T06:09:17Z","timestamp":1763705357490},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2018,2,1]],"date-time":"2018-02-01T00:00:00Z","timestamp":1517443200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Ministry of Science and Technology, R.O.C."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,2]]},"DOI":"10.1109\/taslp.2017.2778948","type":"journal-article","created":{"date-parts":[[2017,11,30]],"date-time":"2017-11-30T19:40:53Z","timestamp":1512070853000},"page":"394-405","source":"Crossref","is-referenced-by-count":5,"title":["Unsupervised Discovery of Structured Acoustic Tokens With Applications to Spoken Term Detection"],"prefix":"10.1109","volume":"26","author":[{"given":"Cheng-Tao","family":"Chung","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin-Shan","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289081"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1109\/TASL.2009.2037404","article-title":"Performance analysis for lattice-based speech indexing approaches using words and subword units","volume":"18","author":"pan","year":"2010","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref32","first-page":"2385","article-title":"Using articulatory features and inferred phonological segments in zero resource speech processing","author":"baljekar","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277847"},{"key":"ref30","first-page":"314","article-title":"Rapid and accurate spoken term detection","author":"miller","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref37","first-page":"821","article-title":"Rapid evaluation of speech representations for spoken term discovery","author":"carlin","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1326571.1326582"},{"key":"ref35","first-page":"1803","article-title":"Resources for speech research: Present and future infrastructure needs","author":"boves","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref34","article-title":"Lattice-based search for spoken utterance retrieval","volume":"51","author":"saraclar","year":"2004","journal-title":"Urbana"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404801"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179087"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639283"},{"key":"ref2","first-page":"2141","article-title":"Unsupervised hidden Markov modeling of spoken queries for spoken term detection without speech recognition","author":"chan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref1","first-page":"16","article-title":"Speech recognition and keyword spotting for low-resource languages: Babel project research at CUED","author":"gales","year":"0","journal-title":"Proc Spoken Lang Technol Under-Resour Lang"},{"key":"ref20","first-page":"1935","article-title":"Unsupervised training of an HMM-based speech recognizer for topic classification","author":"gish","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855121"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639239"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707729"},{"key":"ref23","first-page":"5231","article-title":"Enhancing automatically discovered multi-level acoustic patternsconsidering context Consistency with applications in spoken term detection","author":"chung","year":"0","journal-title":"Proc Acoust Speech Signal Process"},{"key":"ref26","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":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495637"},{"key":"ref50","article-title":"The nni query-by-example system for mediaeval 2015","author":"hou","year":"0","journal-title":"Proc MediaEval"},{"key":"ref51","article-title":"Mediaeval 2013 spoken web search task: System performance measures","author":"rodriguez-fuentes","year":"2013","journal-title":"Dept of Electrical and Electronics"},{"key":"ref59","first-page":"3194","article-title":"Using articulatory features and inferred phonological segments in zero resource speech processing","author":"baljekar","year":"0","journal-title":"Proc INTERSPEECH ISCA"},{"key":"ref58","first-page":"3174","article-title":"Discovering discrete subword units with binarized autoencoders and hidden-markov-model encoders","author":"badino","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref57","first-page":"3179","article-title":"A hybrid dynamic time warping-deep neural network architecture for unsupervised acoustic modeling","author":"thiolliere","year":"0","journal-title":"Annu Conf Int Speech Commun Assoc"},{"key":"ref56","first-page":"1","article-title":"Evaluating speech features with the minimal-pair ABX task: Analysis of the classical MFC\/PLP pipeline","author":"schatz","year":"0","journal-title":"Proc INTERSPEECH 2013 14th Annu Conf Int Speech Commun Assoc"},{"key":"ref55","first-page":"167","article-title":"The formosan language archive: Linguistic analysis and language processing","volume":"10","author":"zeitoun","year":"2005","journal-title":"Computat Linguistics Chinese Language Processing"},{"key":"ref54","first-page":"1","article-title":"Current Developments in Comparative Austronesian Studies","author":"fox","year":"2004","journal-title":"Bahasa Sastra dan Budaya Austronesia di Tengah Era Global dan Dinamika Multikultural"},{"key":"ref53","first-page":"1968","article-title":"A comparison of auditory features for robust speech recognition","author":"kelly","year":"0","journal-title":"Proc 2010 18th Eur Signal Process Conf"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179090"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-691"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-313"},{"key":"ref40","first-page":"1909","article-title":"A piecewise aggregate approximation lower-bound estimate for posteriorgram-based dynamic time warping","author":"zhang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref12","first-page":"1722","article-title":"Intrinsic spectral analysis based on temporal context features for query-by-example spoken term detection","author":"yang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2387382"},{"key":"ref14","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":"ref15","article-title":"Unsupervised Speech Processing with Applications to query-by-example Spoken Term Detection","author":"zhang","year":"0"},{"key":"ref16","first-page":"3625","article-title":"Rapid adaptation for deep neural networks through multi-task learning","author":"huang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.909282"},{"key":"ref18","first-page":"2466","article-title":"Indexing raw acoustic features for scalable zero resource search","author":"jansen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref19","first-page":"1693","article-title":"Towards unsupervised training of speaker independent acoustic models","author":"jansen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2013.05.002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947338"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960579"},{"key":"ref5","first-page":"40","article-title":"A nonparametric Bayesian approach to acoustic model discovery","author":"lee","year":"0","journal-title":"Proc 50th Annu Meeting Assoc for Comput Linguist Long Papers-Vol 1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.04.008"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953141"},{"key":"ref49","article-title":"But quesst 2015 system description","author":"sk\u00e1cel","year":"0","journal-title":"Proc MediaEval"},{"key":"ref9","first-page":"5838","article-title":"Coping with channel mismatch in query-by-example-but QUESST 2014","author":"sz\u00f6ke","year":"0","journal-title":"Proc EEE Int Conf Acoust Speech Signal Process"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1984.tb00034.x"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366913"},{"key":"ref48","article-title":"CUNY systems for the query-by-example search on speech task at mediaeval 2015","author":"ma","year":"0","journal-title":"Proc MediaEval"},{"key":"ref47","article-title":"Speed@ mediaeval 2015: Multilingual phone recognition approach to query by example std","author":"caranica","year":"0"},{"key":"ref42","article-title":"Query by example search on speech at mediaeval","author":"sz\u00f6ke","year":"0"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289085"},{"key":"ref44","article-title":"Updateable PAT-Tree approach to Chinese key phrase extraction using mutual information: A linguistic foundation for knowledge management","author":"ong","year":"0","journal-title":"Proceedings of the Second Asian Digital Library Conference"},{"key":"ref43","first-page":"3169","article-title":"The zero resource speech challenge 2015","author":"versteegh","year":"0","journal-title":"Proc INTERSPEECH"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8186325\/08125178.pdf?arnumber=8125178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:24:17Z","timestamp":1642004657000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8125178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2]]},"references-count":59,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2778948","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,2]]}}}