{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:06:54Z","timestamp":1776888414151,"version":"3.51.2"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096225","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["LiteG2P: A Fast, Light and High Accuracy Model for Grapheme-to-Phoneme Conversion"],"prefix":"10.1109","author":[{"given":"Chunfeng","family":"Wang","sequence":"first","affiliation":[{"name":"Bytedance AI-Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peisong","family":"Huang","sequence":"additional","affiliation":[{"name":"Bytedance AI-Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxiang","family":"Zou","sequence":"additional","affiliation":[{"name":"Bytedance AI-Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Bytedance AI-Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shichao","family":"Liu","sequence":"additional","affiliation":[{"name":"Bytedance AI-Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Yin","sequence":"additional","affiliation":[{"name":"Bytedance AI-Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zejun","family":"Ma","sequence":"additional","affiliation":[{"name":"Bytedance AI-Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178767"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1954"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLR (Poster)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/app9061143"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-449"},{"key":"ref2","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards End-to-End Speech Synthesis","author":"wang","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref17","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-584"},{"key":"ref18","author":"hendrycks","year":"2016","journal-title":"Gaussian error linear units (gelus)"},{"key":"ref8","article-title":"Pronunciation of proper names with a joint n-gram model for bidirectional grapheme-to-phoneme conversion","author":"galescu","year":"2002","journal-title":"Seventh International Conference on Spoken Language Processing"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.01.002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-654"},{"key":"ref4","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref3","first-page":"3146","article-title":"Finegrained prosody modeling in neural speech synthesis using tobi representation","author":"zou","year":"2021","journal-title":"InterSpeech"},{"key":"ref6","article-title":"Issues in building general letter to sound rules","author":"black","year":"1998","journal-title":"The Third ESCA\/COCOSDA Workshop on Speech Synthesis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054250"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096225.pdf?arnumber=10096225","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:07:05Z","timestamp":1700489225000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096225\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096225","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}