{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T18:14:21Z","timestamp":1729620861595,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,10]]},"DOI":"10.1109\/apsipa.2013.6694162","type":"proceedings-article","created":{"date-parts":[[2014,1,15]],"date-time":"2014-01-15T19:01:14Z","timestamp":1389812474000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Speaker-invariant and rhythm-sensitive representation of spoken words"],"prefix":"10.1109","author":[{"given":"Nobuaki","family":"Minematsu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yousuke","family":"Ozaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keikichi","family":"Hirose","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donna","family":"Erickson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1515\/9783110889451"},{"key":"35","first-page":"107","article-title":"On the major class features and syllable theory","author":"selkirk","year":"1984","journal-title":"Language Sound Structure Studies in Phonology"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1515\/9783110206838"},{"key":"36","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1017\/CBO9780511627736.017","article-title":"The role of the sonority cycle in core syllabification","author":"clements","year":"1990","journal-title":"Papers in Laboratory Phonology I Between the Grammar and the Physics of Speech"},{"journal-title":"Speech Hearing and Neural Network","year":"1990","author":"nakagawa","key":"18"},{"key":"33","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-173","article-title":"Discriminative reranking for LVCSR leveraging invariant structure","author":"suzuki","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"15","first-page":"1","article-title":"The rhythm-based prosodic bootstrapping hypothesis of early language acquisition: Does it work for learning for all languages?","volume":"132","author":"mazuka","year":"2007","journal-title":"Gengo Kenkyu"},{"year":"0","key":"34"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2010.5684477"},{"key":"39","doi-asserted-by":"publisher","DOI":"10.1109\/WSS.2002.1224368"},{"key":"13","first-page":"35","article-title":"Implementation of robust speech recognition by simulating infants' speech perception based on the invariant sound shape embedded in utterances","author":"minematsu","year":"2009","journal-title":"Proc Speech and Computer (SPECOM)"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78197-4_4"},{"journal-title":"A dictionary of linguistics and phonetics","year":"1997","author":"crystal","key":"37"},{"key":"11","doi-asserted-by":"crossref","first-page":"2918","DOI":"10.21437\/Interspeech.2010-758","article-title":"Learning speaker normalization using semisupervised manifold alignment","author":"plummer","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"38","article-title":"The syllable in phonological theory","author":"blevins","year":"1995","journal-title":"The Handbook of Phonological Theory"},{"key":"12","doi-asserted-by":"crossref","first-page":"765","DOI":"10.21437\/Interspeech.2011-290","article-title":"Using imitation to learn infant-adult acoustic mappings","author":"ananthakrishnan","year":"2011","journal-title":"Proc INTERSPEECH"},{"journal-title":"Preliminaries to Speech Analysis","year":"1952","author":"jakobson","key":"21"},{"journal-title":"Notes on the French phonemic pattern","year":"1949","author":"jakobson","key":"20"},{"key":"43","doi-asserted-by":"publisher","DOI":"10.1121\/1.380738"},{"key":"42","first-page":"521","article-title":"performance limits for envelope based automatic syllable segmentation","author":"villing","year":"2006","journal-title":"2006 IET Irish Signals and Systems Conference IET"},{"key":"41","first-page":"2165","article-title":"On the relationship between intra-oral pressure and speech sonority","author":"cros","year":"2005","journal-title":"9th European Conference on Speech Communication and Technology"},{"key":"40","article-title":"Sonority as a basis for rhythmic class discrimination","author":"galves","year":"2002","journal-title":"Proc Speech Prosody"},{"journal-title":"Tohoku Univ and Matsushita 212 Phonemically Balanced Word Corpus","year":"0","key":"45"},{"key":"44","first-page":"557","article-title":"Development of English speech database read by Japanese to support CALL research","author":"minematsu","year":"2004","journal-title":"Proc Int Conf Acoustics"},{"key":"22","article-title":"From knowledge-ignorant to knowledge-rich modeling: A new speech research paradigm for next generation automatic speech recognition","author":"lee","year":"2004","journal-title":"Proc ICSLP"},{"key":"23","first-page":"1825","article-title":"An overview on automatic speech attribute transcription (ASAT)","author":"lee","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"24","first-page":"1110","article-title":"Orthogonalized distinctive phonetic feature extraction for noise-robust automatic speech recognition","volume":"e87 d","author":"fukuda","year":"2004","journal-title":"The Institute of Electronics Information and Communication Engineers (IEICE) Transactions on Information and Systems"},{"key":"25","first-page":"299","article-title":"Information-type measures of difference of probability distributions and indirect","volume":"2","author":"csiszar","year":"1967","journal-title":"Stud Sci Math Hung"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.848881"},{"key":"27","first-page":"363","article-title":"Rotational properties of vocal tract length difference in cepstral space","volume":"15","author":"saito","year":"2011","journal-title":"Journal of Research Institute of Signal Processing"},{"key":"28","article-title":"Speech perception and implicit memory: Evidence for detailed episodic encoding of phonetic events","author":"lachs","year":"2000","journal-title":"Rethinking Implicit Memory"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8721.2008.00580.x"},{"journal-title":"Invariance and Variability of Speech Processes","year":"1986","author":"perkell","key":"3"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373493"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607807"},{"key":"1","first-page":"2581","article-title":"A comparison of the data requirements of automatic speech recognition systems and human listeners","author":"moore","year":"2003","journal-title":"Proc INTERSPEECH"},{"journal-title":"Messages to All My Colleagues Living on the Planet","year":"2005","author":"higashida","key":"30"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1007\/s00354-009-0091-y"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415257"},{"key":"32","doi-asserted-by":"crossref","first-page":"993","DOI":"10.21437\/Interspeech.2011-407","article-title":"Continuous digits recognition leveraging invariant structure","author":"suzuki","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2006.03.006"},{"journal-title":"Autism Explaining the Enigma","year":"2003","author":"frith","key":"31"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-0277(01)00157-3"},{"key":"9","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1016\/j.specom.2012.05.001","article-title":"Computational modeling of phonetic and lexical learning in early language acquisition: Existing models and future directions","volume":"54","author":"ra?sa?nen","year":"2012","journal-title":"Speech Communication"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2010.2047340"}],"event":{"name":"2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","start":{"date-parts":[[2013,10,29]]},"location":"Kaohsiung, Taiwan","end":{"date-parts":[[2013,11,1]]}},"container-title":["2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6682637\/6694103\/06694162.pdf?arnumber=6694162","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,23]],"date-time":"2022-03-23T18:27:24Z","timestamp":1648060044000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6694162\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,10]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/apsipa.2013.6694162","relation":{},"subject":[],"published":{"date-parts":[[2013,10]]}}}