{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T02:34:19Z","timestamp":1772159659763,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Department of Science and Technology, Government of India","award":["IMP\/2018\/000986"],"award-info":[{"award-number":["IMP\/2018\/000986"]}]},{"name":"Natural Language Translation Mission","award":["11(1)\/2020-HCC(TDIL)"],"award-info":[{"award-number":["11(1)\/2020-HCC(TDIL)"]}]},{"name":"Ministry of Electronics and Information Technology (MeitY), GoI"},{"name":"Speech to Speech Machine Translation","award":["SA\/NL\/2018(G)&(C)"],"award-info":[{"award-number":["SA\/NL\/2018(G)&(C)"]}]},{"name":"Office of the Principal Scientific Adviser (PSA), GoI"},{"name":"Speech Technologies in Indian Languages","award":["SP\/21-22\/1960\/CSMEIT\/003119"],"award-info":[{"award-number":["SP\/21-22\/1960\/CSMEIT\/003119"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2022.3230453","type":"journal-article","created":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T14:52:01Z","timestamp":1671461521000},"page":"734-747","source":"Crossref","is-referenced-by-count":8,"title":["Exploring the Role of Language Families for Building Indic Speech Synthesisers"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7913-9336","authenticated-orcid":false,"given":"Anusha","family":"Prakash","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, India"}]},{"given":"Hema A.","family":"Murthy","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology Madras, Chennai, India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref3","article-title":"Census of India 2011","year":"2011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2663"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-35"},{"key":"ref7","first-page":"291","article-title":"A common attribute based unified HTS framework for speech synthesis in Indian languages","volume-title":"Proc. Speech Synth. Workshop","author":"Ramani","year":"2013"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"issue":"2","key":"ref10","first-page":"23","article-title":"A new algorithm for data compression","volume":"12","author":"Gage","year":"1994","journal-title":"C Users J."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1127"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/BF02703316"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1002\/9781444335262.wbctp0037","volume-title":"Geminates","author":"Davis","year":"2011"},{"key":"ref15","volume-title":"Aspects of Hindi Phonology","author":"Ohala","year":"1983"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511486876"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1999-203"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-521"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415035"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.05.003"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2187195"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472737"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-017-0659-6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683519"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1590"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2679"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-30"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-7"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2003.1198768"},{"key":"ref30","first-page":"137","article-title":"An HMM-based bilingual (Mandarin-English) TTS","volume-title":"Proc. Speech Synth. Workshop","author":"Liang","year":"2007"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1178"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682927"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3191"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2654"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1821"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1163"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-345"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/vcc_bc.2020-14"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2008.4777837"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472738"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-172"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-37"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-17"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2664"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IALP.2017.8300579"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053642"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054305"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-22"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-327"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2668"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2070"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414226"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1869"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1632"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3430984.3431034"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-28"},{"key":"ref58","article-title":"Multilingual byte2speech text-to-speech models are few-shot spoken language learners","author":"He","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1265"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1565"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-242"},{"key":"ref62","first-page":"37","article-title":"Resources for Indian languages","volume-title":"Proc. Community-Based Building Lang. Resour. (Int. Conf. Text, Speech, Dialogue)","author":"Baby","year":"2016"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-45510-5_59"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref66","article-title":"The LJ speech dataset","author":"Ito","year":"2017"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref68","volume-title":"Method for the Subjective Assessment of Intermediate Sound Quality (MUSHRA)","year":"2001"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/icslp.2002-303"},{"key":"ref71","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref73","first-page":"3165","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 32: Annu. Conf. Neural Inf. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref74","first-page":"2021","article-title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/09992058.pdf?arnumber=9992058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T22:10:37Z","timestamp":1710367837000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9992058\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3230453","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.21435756","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.21435756.v1","asserted-by":"object"}]},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}