{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:13:51Z","timestamp":1740172431037,"version":"3.37.3"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"NSF","award":["IS 19-10319"],"award-info":[{"award-number":["IS 19-10319"]}]},{"name":"RI: Small: Collaborative Research: Automatic Creation of New Phone Inventories"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2022.3178238","type":"journal-article","created":{"date-parts":[[2022,5,27]],"date-time":"2022-05-27T21:01:53Z","timestamp":1653685313000},"page":"1918-1926","source":"Crossref","is-referenced-by-count":1,"title":["Autosegmental Neural Nets 2.0: An Extensive Study of Training Synchronous and Asynchronous Phones and Tones for Under-Resourced Tonal Languages"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0092-8071","authenticated-orcid":false,"given":"Jialu","family":"Li","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering and Beckman Institute of Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5631-2893","authenticated-orcid":false,"given":"Mark","family":"Hasegawa-Johnson","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering and Beckman Institute of Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139164559","volume-title":"Tone","author":"Yip","year":"2002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0142060"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1159\/000028432"},{"key":"ref4","first-page":"2359","article-title":"A pitch target approximation model for F0 contours in Mandarin","volume-title":"Proc. Interspeech","author":"Xu","year":"1999"},{"key":"ref5","first-page":"135","article-title":"Tone melodies and the autosegment","volume-title":"Proc. 6th Conf. Afr. Linguistics, Ohio State Univ. Work. Papers Linguistics","author":"Goldsmith","year":"1975"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1163\/1570-6699_eall_eall_dum_0021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/29.52701"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319276"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/595576.595581"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/1.2717413"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707740"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2015.7357876"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"article-title":"Deep speech: Scaling up end-to-end speech recognition","year":"2014","author":"Hannun","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424246"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.859138"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.09.001"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639655"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682918"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683607"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472152"},{"key":"ref23","first-page":"96","article-title":"Massive multilingual adversarial speech recognition","volume-title":"Proc. Annu. Conf. North Amer. Chapter Assoc. Comput. Linguistics","author":"Adams","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268932"},{"key":"ref25","first-page":"53","article-title":"Phonemic transcription of low-resource tonal languages","volume-title":"Proc. Australas. Lang. Technol. Assoc. Workshop","author":"Adams","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683859"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489589"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1834"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.07.008"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424230"},{"key":"ref31","first-page":"26","article-title":"Building an ASR system for a low-resource language through the adaptation of a high-resource language ASR system: Preliminary results","volume-title":"Proc. Int. Conf. Natural Lang., Signal, Speech Process.","author":"Scharenborg","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2513"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"Oord","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1843"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2561"},{"article-title":"Mandarin tone modeling using recurrent neural networks","year":"2017","author":"Huang","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23538-2_6"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1992-260"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-006-8534-z"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639248"},{"article-title":"IARPA Babel Cantonese language pack IARPA-babel101b-v0.4c","year":"2016","author":"Andrus","key":"ref42"},{"article-title":"IARPA Babel Lao language pack IARPA-babel203b-v3.1a","year":"2017","author":"Andrus","key":"ref43"},{"article-title":"IARPA Babel Vietnamese language pack IARPA-babel107b-v0.7","year":"2017","author":"Andrus","key":"ref44"},{"key":"ref45","article-title":"1997 Mandarin broadcast news speech (HUB4-NE) LDC98S73","volume-title":"Web Download","author":"Huang","year":"1998"},{"journal-title":"gitHub repository","article-title":"Prepare globalphone","author":"elasko","key":"ref46"},{"key":"ref47","article-title":"jameslyons\/python_speech_features: release v0.6.1","volume-title":"Web Download","author":"Huang","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-654"},{"article-title":"Chinese tone sandhi and prosody","year":"1997","author":"Lee","key":"ref49"},{"key":"ref50","first-page":"261","article-title":"Voice quality and tone in several lao dialects","volume-title":"Proc. 5th Annu. Meeting Southeast Asian Linguistics Soc.","author":"Person","year":"1995"},{"key":"ref51","first-page":"119","article-title":"The coarticulation of tones: An acoustic study of Thai","volume-title":"Haskins Lab.: Status Rep. Speech Res. SR-44","author":"Abramson","year":"1975"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1159\/000262208"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.4324\/9780203500088"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1121\/1.1911939"},{"volume-title":"International Phonetic Association, Ed., Handbook of the International Phonetic Association","year":"1999","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054362"},{"key":"ref57","first-page":"185","article-title":"XNMT: The extensible neural machine translation toolkit","volume-title":"Proc. Conf. Assoc. Mach. Transl. Americas Open Source Softw. Showcase","author":"Neubig","year":"2018"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-29"},{"volume-title":"Concise Dictionary of Spoken Chinese","year":"1947","author":"Zhao","key":"ref59"},{"key":"ref60","article-title":"The identity of non-identified sounds: Glottal stop, prevocalic\/w\/and triphthongs in vietnamese","volume":"34","author":"Pham","year":"2009","journal-title":"Toronto Work. Papers Linguistics"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3109\/17549507.2015.1101162"},{"key":"ref62","first-page":"135","article-title":"On the origins of labialized consonants in Lao","volume-title":"Proc. Papers from sixth Annu. meeting Southeast Asian Linguistic Soc.","author":"Erickson","year":"2001"},{"issue":"1","key":"ref63","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1017\/S0025100300004746","article-title":"Thai","volume":"23","author":"Tingsabadh","year":"1993","journal-title":"J. Int. Phonetic Assoc."},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266481"},{"article-title":"Sctk, the nist scoring toolkit","year":"2018","author":"Fiscus","key":"ref65"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6570655\/9657755\/9783062-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09783062.pdf?arnumber=9783062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T02:03:00Z","timestamp":1706752980000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9783062\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3178238","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2022]]}}}