{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:58:54Z","timestamp":1764403134845,"version":"3.37.3"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001695","name":"JST","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001695","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9687904","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"749-756","source":"Crossref","is-referenced-by-count":6,"title":["Low-Latency Incremental Text-to-Speech Synthesis with Distilled Context Prediction Network"],"prefix":"10.1109","author":[{"given":"Takaaki","family":"Saeki","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.jml.2019.104047"},{"key":"ref33","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions and reversals","volume":"10","author":"levenshtein","year":"1966","journal-title":"Soviet Physics Doklady"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","volume":"abs 1412 6980","author":"kingma","year":"2014","journal-title":"ArXiv"},{"journal-title":"Gentle A robust yet lenient forced aligner built on Kaldi","year":"2017","author":"ochshorn","key":"ref31"},{"journal-title":"The LJ speech dataset","year":"2017","author":"ito","key":"ref30"},{"key":"ref37","first-page":"333","author":"seleskovitch","year":"1978","journal-title":"Language and Cognition"},{"key":"ref36","article-title":"ESP-net: End-to-end speech processing toolkit","volume":"abs 1804 15","author":"watanabe","year":"2018","journal-title":"ArXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.346"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1177\/1745691610393980"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3073869"},{"journal-title":"Language Models are Unsupervised Multitask Learners","year":"2019","author":"radford","key":"ref12"},{"journal-title":"Transformer to CNN Label-scarce distillation for efficient text classification","year":"2018","author":"chia","key":"ref13"},{"key":"ref14","article-title":"Distilling task-specific knowledge from BERT into simple neural networks","volume":"abs 1903 12136","author":"tang","year":"2019","journal-title":"ArXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/341"},{"key":"ref16","article-title":"Tacotron: Towards end-to-end speech synthesis","volume":"abs 1609 3499","author":"wang","year":"2017","journal-title":"ArXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref18","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2103"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref4","article-title":"End-to-end adversarial text-to-speech","author":"donahue","year":"0","journal-title":"Proc ICLR"},{"key":"ref27","article-title":"Style Tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume":"abs 1803 9017","author":"wang","year":"2018","journal-title":"ArXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413851"},{"key":"ref6","article-title":"Simultaneous speech-to-speech translation system with neural incremental ASR, MT, and TTS","volume":"abs 2011 4845","author":"sudoh","year":"2020","journal-title":"ArXiv"},{"key":"ref29","article-title":"WaveGlow: A flow-based generative network for speech synthesis","volume":"abs 1811 2","author":"prenger","year":"2018","journal-title":"ArXiv"},{"key":"ref5","first-page":"437","article-title":"Real-time incremental speech-to-speech translation of dialogs","author":"bangalore","year":"2012","journal-title":"Proc NAACL"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1110"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.349"},{"key":"ref2","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"0","journal-title":"Proc ICLR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-33"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1822"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-275"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2464"},{"key":"ref24","article-title":"Do deep nets really need to be deep?","author":"ba","year":"2014","journal-title":"Proc NIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414809"},{"key":"ref26","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL"},{"key":"ref25","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2014","journal-title":"Proc NIPS Deep Learning and Representation Learning Workshop"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09687904.pdf?arnumber=9687904","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:41:57Z","timestamp":1652733717000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687904\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9687904","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}