{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:35:22Z","timestamp":1767339322851,"version":"3.37.3"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T00:00:00Z","timestamp":1666828800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T00:00:00Z","timestamp":1666828800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC)","doi-asserted-by":"publisher","award":["62206136"],"award-info":[{"award-number":["62206136"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFE0122900"],"award-info":[{"award-number":["2018YFE0122900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,27]]},"DOI":"10.1109\/ialp57159.2022.9961271","type":"proceedings-article","created":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T21:07:51Z","timestamp":1670015271000},"page":"184-189","source":"Crossref","is-referenced-by-count":4,"title":["MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied Baseline"],"prefix":"10.1109","author":[{"given":"Yifan","family":"Hu","sequence":"first","affiliation":[{"name":"College of Computer Science, Inner Mongolia University,Hohhot,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengkai","family":"Yin","sequence":"additional","affiliation":[{"name":"College of Computer Science, Inner Mongolia University,Hohhot,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Inner Mongolia University,Hohhot,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feilong","family":"Bao","sequence":"additional","affiliation":[{"name":"College of Computer Science, Inner Mongolia University,Hohhot,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanglai","family":"Gao","sequence":"additional","affiliation":[{"name":"College of Computer Science, Inner Mongolia University,Hohhot,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054563"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701851"},{"journal-title":"Char2Wav End-to-end speech synthesis","year":"2017","author":"sotelo","key":"ref10"},{"key":"ref11","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","author":"arik","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref12","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref14","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"ArXiv Preprint"},{"journal-title":"Neural Speech Synthesis with Transformer Network","year":"2018","author":"li","key":"ref16"},{"key":"ref17","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.29007\/qwpk"},{"key":"ref19","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36802-9_68"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97304-3_17"},{"journal-title":"The LJ speech dataset","year":"2017","author":"ito","key":"ref3"},{"key":"ref6","article-title":"A language vitality assessment for mongolian in inner mongolia, china","author":"puthuval","year":"2017","journal-title":"Proceedings of the 2nd Conference on Central Asian Languages and Linguistics"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"},{"key":"ref5","article-title":"Aishell-3: A multi-speaker mandarin tts corpus and the baselines","author":"shi","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/1-4020-8039-5_2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-971X.2005.00404.x"},{"key":"ref2","article-title":"A survey on neural speech synthesis","author":"tan","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338"},{"journal-title":"CSTR VCTK corpus English multi-speaker corpus for cstr voice cloning toolkit","year":"2016","author":"veaux","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref21","first-page":"5410","article-title":"Almost unsupervised text to speech and automatic speech recognition","author":"ren","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3040523"},{"key":"ref23","article-title":"End-to-end text-to-speech for low-resource languages by cross-lingual transfer learning","author":"tu","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IALP54817.2021.9675192"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706263"}],"event":{"name":"2022 International Conference on Asian Language Processing (IALP)","start":{"date-parts":[[2022,10,27]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,10,28]]}},"container-title":["2022 International Conference on Asian Language Processing (IALP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9961216\/9961238\/09961271.pdf?arnumber=9961271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:04:01Z","timestamp":1671480241000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9961271\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,27]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/ialp57159.2022.9961271","relation":{},"subject":[],"published":{"date-parts":[[2022,10,27]]}}}