{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T19:54:13Z","timestamp":1769457253545,"version":"3.49.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2017,10,1]],"date-time":"2017-10-01T00:00:00Z","timestamp":1506816000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2017,10]]},"DOI":"10.1109\/taslp.2017.2729024","type":"journal-article","created":{"date-parts":[[2017,7,19]],"date-time":"2017-07-19T18:09:13Z","timestamp":1500487753000},"page":"1914-1928","source":"Crossref","is-referenced-by-count":7,"title":["Unsupervised Iterative Deep Learning of Speech Features and Acoustic Tokens with Applications to Spoken Term Detection"],"prefix":"10.1109","volume":"25","author":[{"given":"Cheng-Tao","family":"Chung","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng-Yu","family":"Tsai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chia-Hsiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin-Shan","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","volume":"2","author":"young","year":"1997","journal-title":"The HTK Book"},{"key":"ref38","article-title":"zrst","author":"chung","year":"2014"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref32","first-page":"448","article-title":"Deep Boltzmann machines","author":"salakhutdinov","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref31","first-page":"993","article-title":"Latent\n Dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1117\/12.292778"},{"key":"ref37","author":"pitt","year":"2007","journal-title":"Buckeye corpus of conversational speech (2nd release)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289082"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366913"},{"key":"ref34","first-page":"2341","article-title":"I-vector based speaker recognition on short utterances","author":"kanagasundaram","year":"0","journal-title":"Proc 12th Annu Conf Int Speech Commun Assoc"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1187415.1187418"},{"key":"ref27","first-page":"2838","article-title":"Improved topic classification and\n keyword discovery using an HMM-based speech recognizer trained without supervision","author":"siu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref29","first-page":"1676","article-title":"Towards\n spoken term discovery at scale with zero resources","author":"jansen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref2","first-page":"5838","article-title":"Coping with channel mismatch in\n query-by-example-but QUESST 2014","author":"sz\u00f6ke","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","first-page":"3169","article-title":"The Zero Resource Speech Challenge 2015","author":"versteegh","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2013.05.002"},{"key":"ref21","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179089"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179087"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2011.6085989"},{"key":"ref25","first-page":"501","article-title":"A segment\n model based approach to speech recognition","author":"lee","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref50","first-page":"3189","article-title":"Parallel inference of Dirichlet process Gaussian mixture models for unsupervised\n acoustic modeling: A feasibility study","author":"chen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref51","first-page":"3194","article-title":"Using articulatory features\n and inferred phonological segments in zero resource speech processing","author":"baljekar","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref57","first-page":"2237","article-title":"Phonotactic language identification using high quality phoneme recognition","author":"matejka","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref56","first-page":"641","article-title":"Adaptor grammars: A framework for specifying compositional nonparametric Bayesian models","author":"johnson","year":"0","journal-title":"Proc Adv Neural Inf Process Syst Conf"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163965"},{"key":"ref54","first-page":"560","article-title":"Bridging the gap between speech technology and\n natural language processing: An evaluation toolbox for term discovery systems","author":"ludusan","year":"0","journal-title":"Proc Lang Resources Eval Conf"},{"key":"ref53","first-page":"3209","article-title":"An\n evaluation of graph clustering methods for unsupervised term discovery","author":"lyzinski","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref52","first-page":"3204","article-title":"Unsupervised word discovery from speech using automatic segmentation into syllable-like units","author":"r\u00e4s\u00e4nen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref10","first-page":"2466","article-title":"Indexing raw acoustic features for scalable zero resource search","author":"jansen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref11","first-page":"1693","article-title":"Towards unsupervised training of speaker independent acoustic models","author":"jansen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref40","first-page":"257","article-title":"SRILM—An extensible language modeling toolkit","author":"stolcke","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref12","first-page":"1935","article-title":"Unsupervised training of an HMM-based\n speech recognizer for topic classification","author":"gish","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639239"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855121"},{"key":"ref15","first-page":"5231","article-title":"Enhancing automatically discovered\n multi-level acoustic patternsconsidering context consistency with applications in spoken term detection","author":"chung","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707729"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404801"},{"key":"ref18","first-page":"825","article-title":"Investigating the learning effect of multilingual bottle-neck features for ASR","author":"vu","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424246"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-313"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-691"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2387382"},{"key":"ref5","first-page":"1722","article-title":"Intrinsic spectral analysis based on temporal context features for\n query-by-example spoken term detection.","author":"yang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref8","article-title":"Unsupervised speech processing with applications to\n query-by-example spoken term detection","author":"zhang","year":"2013"},{"key":"ref7","first-page":"3199","article-title":"A comparison of neural network methods\n for unsupervised representation learning on the zero resource speech challenge","author":"renshaw","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref49","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":"ref9","first-page":"3625","article-title":"Rapid adaptation for deep neural networks through multi-task learning.","author":"huang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277790"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383172"},{"key":"ref48","first-page":"3179","article-title":"A hybrid dynamic time warping-deep neural network architecture for\n unsupervised acoustic modeling","author":"thiolliere","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref41","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref44","first-page":"915","article-title":"Evaluating speech features with the minimal-pair ABX task (ii): Resistance to noise","author":"schatz","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref43","first-page":"1","article-title":"Evaluating speech features with the minimal-pair ABX task: Analysis of the classical MFC\/PLP\n pipeline","author":"schatz","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8015274\/07984872.pdf?arnumber=7984872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:04:13Z","timestamp":1642003453000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7984872\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10]]},"references-count":57,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2729024","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,10]]}}}