{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:34:40Z","timestamp":1730298880205,"version":"3.28.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,13]],"date-time":"2021-10-13T00:00:00Z","timestamp":1634083200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,13]],"date-time":"2021-10-13T00:00:00Z","timestamp":1634083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,13]],"date-time":"2021-10-13T00:00:00Z","timestamp":1634083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,13]]},"DOI":"10.1109\/sped53181.2021.9587350","type":"proceedings-article","created":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T20:53:34Z","timestamp":1635800014000},"page":"156-161","source":"Crossref","is-referenced-by-count":0,"title":["Autoregressive Articulatory WaveNet Flow for Speaker-Independent Acoustic-to-Articulatory Inversion"],"prefix":"10.1109","author":[{"given":"Narjes","family":"Bozorg","sequence":"first","affiliation":[]},{"given":"Michael T.","family":"Johnson","sequence":"additional","affiliation":[]},{"given":"Mohammad","family":"Soleymanpour","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855102"},{"key":"ref38","article-title":"Wavenet: A generative model for raw audio","volume":"abs 1609 3499","author":"van den oord","year":"2016","journal-title":"CoRR"},{"key":"ref33","article-title":"Announcing the electromagnetic articulography (day 1) subset of the mngu0 articulatory corpus","author":"richmond","year":"2011","journal-title":"Twelfth Annual Conference of the International Speech Communication Association"},{"key":"ref32","first-page":"305","article-title":"A multichannel articulatory database and its application for automatic speech recognition","author":"wrench","year":"2000","journal-title":"Proceedings 5 Th Seminar of Speech Production"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706709"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1202"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPIT47144.2019.9001752"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947385"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1121\/1.3514544"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPIT.2018.8705093"},{"key":"ref10","article-title":"Acoustic theory of speech production (mouton, the hague)(1970)","author":"fant","year":"1960","journal-title":"The closely spaced horizontal lines shown in Fig 1A are the harmonics of the fundamental frequency of phonation and are typically revealed in narrowband spectrograms"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref11","article-title":"An empirical investigation of the nonuniqueness in the acoustic-to-articulatory mapping","author":"qin","year":"2007","journal-title":"Eighth Annual Conference of the International Speech Communication Association"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1121\/1.3455847"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.381848"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1121\/1.1921448"},{"key":"ref15","first-page":"237","article-title":"Acoustic-to-articulatory inversion using dynamical and phonological constraints","author":"dusan","year":"2000","journal-title":"Proc 5th Seminar on Speech Production"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.09.001"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2008.917004"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-260"},{"key":"ref19","article-title":"Deep architectures for articulatory inversion","author":"uria","year":"2012","journal-title":"Thirteenth Annual Conference of the International Speech Communication Association"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2295"},{"article-title":"Development of kinematic templates for automatic pronunciation assessment using acoustic-to-articulatory inversion","year":"2017","author":"jones","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682506"},{"article-title":"Speaker independent acoustic-to-articulatory inversion","year":"2014","author":"ji","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1843"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178812"},{"article-title":"Independent and automatic evaluation of acoustic-to-articulatory inversion models","year":"2019","author":"maud","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.5116130"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2464702"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2588340"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1399"},{"key":"ref1","first-page":"454","article-title":"Comparison of hmm and tmdn methods for lip synchronisation","author":"hofer","year":"2010"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77347-4_23"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3168"},{"key":"ref21","article-title":"A trajectory mixture density network for the acoustic-articulatory inversion mapping","author":"richmond","year":"2006","journal-title":"Ninth International Conference on Spoken Language Processing"},{"article-title":"Fast wavenet generation algorithm","year":"2016","author":"paine","key":"ref42"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282219"},{"article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","year":"2017","author":"oord","key":"ref41"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706629"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1121\/10.0000738"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.05.004"}],"event":{"name":"2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","start":{"date-parts":[[2021,10,13]]},"location":"Bucharest, Romania","end":{"date-parts":[[2021,10,15]]}},"container-title":["2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9586791\/9587340\/09587350.pdf?arnumber=9587350","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:56:24Z","timestamp":1652201784000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9587350\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,13]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/sped53181.2021.9587350","relation":{},"subject":[],"published":{"date-parts":[[2021,10,13]]}}}