{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:33:14Z","timestamp":1767339194258},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413864","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6563-6567","source":"Crossref","is-referenced-by-count":12,"title":["Speech Bert Embedding for Improving Prosody in Neural TTS"],"prefix":"10.1109","author":[{"given":"Liping","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank K.","family":"Soong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref12"},{"article-title":"Roberta: A robustly optimized bert pretraining approach","year":"2019","author":"liu","key":"ref13"},{"article-title":"Improving transformer-based speech recognition using unsupervised pre-training","year":"2019","author":"jiang","key":"ref14"},{"article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","year":"2020","author":"baevski","key":"ref15"},{"article-title":"Modeling multi-speaker latent space to improve neural tts: Quick enrolling new speaker and enhancing premium voice","year":"2018","author":"deng","key":"ref16"},{"key":"ref17","first-page":"2962","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"gibiansky","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3139"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/CCC50068.2020.9188779"},{"key":"ref4","first-page":"3171","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref6","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018"},{"article-title":"Wavenet: A generative model for raw audio","year":"2016","author":"oord","key":"ref5"},{"article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","year":"2018","author":"skerry-ryan","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017"},{"article-title":"Char2wav: End-to-end speech synthesis","year":"2017","author":"sotelo","key":"ref1"},{"key":"ref9","first-page":"1878","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"The LJ speech dataset","year":"2017","author":"ito","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","year":"2019","author":"yamagishi","key":"ref21"},{"key":"ref23","first-page":"7654","article-title":"ESPnet-TTS: Unified, and integratable open source end-to-end text-to-speech toolkit","author":"hayashi","year":"2020","journal-title":"ICASSP"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413864.pdf?arnumber=9413864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:55Z","timestamp":1652197255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413864\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413864","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}