{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T12:23:24Z","timestamp":1764937404889,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746212","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7132-7136","source":"Crossref","is-referenced-by-count":4,"title":["Polyphone Disambiguation and Accent Prediction Using Pre-Trained Language Models in Japanese TTS Front-End"],"prefix":"10.1109","author":[{"given":"Rem","family":"Hida","sequence":"first","affiliation":[{"name":"Sony Group Corporation,Tokyo,Japan"}]},{"given":"Masaki","family":"Hamada","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Tokyo,Japan"}]},{"given":"Chie","family":"Kamada","sequence":"additional","affiliation":[{"name":"Sony Corporation of America,San Jose,CA,USA"}]},{"given":"Emiru","family":"Tsunoo","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Tokyo,Japan"}]},{"given":"Toshiyuki","family":"Sekiya","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Tokyo,Japan"}]},{"given":"Toshiyuki","family":"Kumakura","sequence":"additional","affiliation":[{"name":"Sony Corporation of America,San Jose,CA,USA"}]}],"member":"263","reference":[{"key":"ref33","first-page":"54","article-title":"FLAIR: An easy-to-use framework for state-of-the-art NLP","author":"akbik","year":"2019","journal-title":"NAACL-Demonstrations '07"},{"key":"ref32","first-page":"2723","article-title":"Word-based partial annotation for efficient corpus construction","author":"neubig","year":"2010","journal-title":"LREC"},{"year":"0","key":"ref31","article-title":"ASJ Japanese Newspaper Article Sentences Read Speech Corpus (JNAS)"},{"article-title":"JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis","year":"2017","author":"sonobe","key":"ref30"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref34","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"ICML"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3177"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1430"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414413"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1757"},{"key":"ref14","first-page":"120","article-title":"Japanese pronunciation prediction as phrasal statistical machine translation","author":"hatori","year":"2011","journal-title":"IJCNLP"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-914"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1094"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003918"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1235"},{"key":"ref19","first-page":"849","article-title":"Accentuation rules for Japanese word concatenation","volume":"66","author":"sagisaka","year":"1983","journal-title":"IEICE Trans Inf and Syst (Japanese Edition)"},{"article-title":"Bidirectional lstm-crf models for sequence tagging","year":"2015","author":"huang","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2020EDP7104"},{"key":"ref27","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"2001","journal-title":"ICML"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-30"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-252"},{"key":"ref29","first-page":"7","article-title":"Corpus of spontaneous Japanese: its design and evaluation","author":"maekawa","year":"2003","journal-title":"IEEE and ISCA Workshop on Spontaneous Speech Processing and Recognition"},{"key":"ref5","first-page":"3361","article-title":"Ctrl-P: Temporal control of prosodic variation for speech synthesis","volume":"5","author":"ram mohan","year":"2021","journal-title":"InterSpeech"},{"key":"ref8","first-page":"281","article-title":"Predicting prosodic prominence from text with pre-trained contextualized word representations","author":"talman","year":"2019","journal-title":"NoDaLiDa"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414935"},{"key":"ref2","article-title":"Fast-Speech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"ICLRE"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1418"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2016AWI0004"},{"key":"ref22","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref21","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref23","first-page":"1638","article-title":"Contextual string embeddings for sequence labeling","author":"akbik","year":"2018","journal-title":"COLING"},{"key":"ref26","first-page":"161","article-title":"Does BERT make any sense? interpretable word sense disambiguation with contextualized embeddings","author":"wiedemann","year":"2019","journal-title":"Konvens"},{"key":"ref25","first-page":"4129","article-title":"A structural probe for finding syntax in word representations","author":"hewitt","year":"2019","journal-title":"NAACL-HLT"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746212.pdf?arnumber=9746212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:11:46Z","timestamp":1660594306000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746212\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746212","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}