{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:13:52Z","timestamp":1740172432758,"version":"3.37.3"},"reference-count":54,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61831022","U21B2010","62101553","61971419","62006223","62276259","62201572","62206278"],"award-info":[{"award-number":["61831022","U21B2010","62101553","61971419","62006223","62276259","62201572","62206278"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009592","name":"Beijing Municipal Science and Technology Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009592","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Administrative Commission of Zhongguancun Science","award":["Z211100004821013"],"award-info":[{"award-number":["Z211100004821013"]}]}],"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.2023.3301235","type":"journal-article","created":{"date-parts":[[2023,8,9]],"date-time":"2023-08-09T17:33:57Z","timestamp":1691602437000},"page":"2963-2973","source":"Crossref","is-referenced-by-count":2,"title":["Adversarial Multi-Task Learning for Mandarin Prosodic Boundary Prediction With Multi-Modal Embeddings"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-4618","authenticated-orcid":false,"given":"Jiangyan","family":"Yi","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Arcial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9344-6428","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9598-1881","authenticated-orcid":false,"given":"Ruibo","family":"Fu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Arcial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1490-6973","authenticated-orcid":false,"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Arcial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3461-3034","authenticated-orcid":false,"given":"Chu Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Arcial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5785-7027","authenticated-orcid":false,"given":"Chenglong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1060"},{"key":"ref12","article-title":"A brief analysis of the formation rule of Mandarin prosodic words","author":"xiong","year":"0","journal-title":"Report of Phonetic Research"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472760"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1400"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref52","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","first-page":"121","article-title":"Specification for corpus processing at peking university: Word segmentation, POS tagging and phonetic notation","volume":"13","author":"yu","year":"2003","journal-title":"Journal of Chinese Language and Computing"},{"key":"ref10","first-page":"61","article-title":"Locating boundaries for prosodic constituents in unrestricted Mandarin texts","volume":"6","author":"chu","year":"2001","journal-title":"Comput Linguist Chinese Lang Process"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-125"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1472"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404780"},{"key":"ref19","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682770"},{"key":"ref51","first-page":"1","article-title":"Language id-based training of multilingual stacked bottleneck features","author":"cutler","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683223"},{"article-title":"Aishell-3: A multi-speaker Mandarin TTS corpus and the baselines","year":"2020","author":"shi","key":"ref46"},{"article-title":"Aishell-2: Transforming mandarin ASR research into industrial scale","year":"2018","author":"du","key":"ref45"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6301"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01716-3_18"},{"key":"ref42","first-page":"1","author":"kraemer","year":"2015","journal-title":"Kappa Coefficient in Wiley StatsRef Statistics Reference Online"},{"key":"ref41","first-page":"253","article-title":"Fast online training with frequency-adaptive learning rates for Chinese word segmentation and new word detection","author":"sun","year":"0","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref44","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"0","journal-title":"Proc 12th USENIX Symp Operating Syst Des Implementation"},{"key":"ref43","first-page":"62","article-title":"Kappa coefficient: A popular measure of rater agreement","volume":"27","author":"tang","year":"2015","journal-title":"Shanghai Archives of Psychiatry"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1429"},{"article-title":"Unified Mandarin TTS front-end based on distilled BERT model","year":"2020","author":"zhang","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-914"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747315"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2935807"},{"key":"ref3","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref6","first-page":"3885","article-title":"Erosodic boundary prediction model for Vietnamese text-to-speech","author":"trang","year":"0","journal-title":"Proc INTERSPEECH"},{"article-title":"A survey on neural speech synthesis","year":"2021","author":"tan","key":"ref5"},{"key":"ref40","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","first-page":"83","article-title":"Task clustering and gating for Bayesian multitask learning","volume":"4","author":"bakker","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref34","first-page":"1","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1110"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639316"},{"key":"ref30","first-page":"165","article-title":"Unsupervised prosodic break detection in Mandarin speech","author":"huang","year":"2009","journal-title":"Johns"},{"key":"ref33","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"0","journal-title":"Proc 1st Int Conf Learn Representations"},{"key":"ref32","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","author":"ganin","year":"0","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2889606"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1001"},{"key":"ref24","first-page":"811","article-title":"Speech2vec: A sequence-to-sequence framework for learning word embeddings from speech","author":"yu-an","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref23","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"J Mach Learn Res"},{"journal-title":"Automatic detection and classification of prosodic events","year":"2009","author":"rosenberg","key":"ref26"},{"key":"ref25","first-page":"567","article-title":"Exploiting task relatedness for mulitple task learning","author":"ben-david","year":"0","journal-title":"Proc 16th Annu Conf Comput Learn Theory"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.917071"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907570"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-71"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-530"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10214083.pdf?arnumber=10214083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,22]],"date-time":"2023-09-22T17:56:23Z","timestamp":1695405383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10214083\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3301235","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2023]]}}}