{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T08:45:30Z","timestamp":1767084330005,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"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":[[2023,10,31]]},"DOI":"10.1109\/apsipaasc58517.2023.10317138","type":"proceedings-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:46Z","timestamp":1700507266000},"page":"2409-2415","source":"Crossref","is-referenced-by-count":2,"title":["Multi-granularity Semantic and Acoustic Stress Prediction for Expressive TTS"],"prefix":"10.1109","author":[{"given":"Wenjiang","family":"Chi","sequence":"first","affiliation":[{"name":"Shanghai Mobvoi Information Technology Co., Ltd,China"}]},{"given":"Xiaoqin","family":"Feng","sequence":"additional","affiliation":[{"name":"Shanghai Mobvoi Information Technology Co., Ltd,China"}]},{"given":"Liumeng","family":"Xue","sequence":"additional","affiliation":[{"name":"Audio, Speech and Language Processing Group (ASLP)"}]},{"given":"Yunlin","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Mobvoi Information Technology Co., Ltd,China"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Audio, Speech and Language Processing Group (ASLP)"}]},{"given":"Zhifei","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Mobvoi Information Technology Co., Ltd,China"}]}],"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":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","year":"2020","author":"Ren","key":"ref4"},{"article-title":"End-to-end adversarial text-to-speech","year":"2020","author":"Donahue","key":"ref5"},{"article-title":"Durian: Duration informed attention network for multimodal synthesis","year":"2019","author":"Yu","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref8","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-947"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/iscslp49672.2021.9362069"},{"key":"ref12","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"international conference on machine learning","author":"Skerry-Ryan"},{"key":"ref13","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"article-title":"Uncovering latent style factors for expressive speech synthesis","year":"2017","author":"Wang","key":"ref15"},{"article-title":"Multi-reference tacotron by intercross training for style disentangling, transfer and control in speech synthesis","year":"2019","author":"Bian","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2016.7918425"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/icslp.1992-260"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-45258-5_6"},{"article-title":"Study on automatic prediction of sentential stress for chinese putonghua text-to-speech system with natural style","year":"2007","author":"Shao","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2004-26"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/icslp.2000-914"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.001"},{"article-title":"Predicting prosodic prominence from text with pre-trained contextualized word representations","year":"2019","author":"Talman","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/YCICT.2009.5382357"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8462473"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1159"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3124365"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2034"},{"article-title":"Bidirectional lstm-crf models for sequence tagging","year":"2015","author":"Huang","key":"ref32"},{"key":"ref33","first-page":"322","article-title":"Efficient higher-order crfs for morphological tagging","volume-title":"Proceedings of the 2013 conference on empirical methods in natural language processing","author":"M\u00fcller"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876129"}],"event":{"name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2023,10,31]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10317071\/10317095\/10317138.pdf?arnumber=10317138","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T18:43:12Z","timestamp":1709404992000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10317138\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc58517.2023.10317138","relation":{},"subject":[],"published":{"date-parts":[[2023,10,31]]}}}