{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T07:14:19Z","timestamp":1766733259952},"reference-count":23,"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\/icassp43922.2022.9747131","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7272-7276","source":"Crossref","is-referenced-by-count":8,"title":["Unified Multimodal Punctuation Restoration Framework for Mixed-Modality Corpus"],"prefix":"10.1109","author":[{"given":"Yaoming","family":"Zhu","sequence":"first","affiliation":[{"name":"ByteDance AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liwei","family":"Wu","sequence":"additional","affiliation":[{"name":"ByteDance AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanbo","family":"Cheng","sequence":"additional","affiliation":[{"name":"ByteDance AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682260"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3074"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414979"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1096"},{"key":"ref14","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL HLT 2019"},{"key":"ref15","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS 2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101155"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-11"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413432"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960690"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-53"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.iwslt-1.33"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-240"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545470"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023200"},{"key":"ref2","first-page":"269","article-title":"A comparison of different punctuation prediction approaches in a translation context","author":"vandeghinste","year":"0","journal-title":"EAMT 2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1352"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953248"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682418"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref21","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"0","journal-title":"NeurIPS 2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"}],"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\/09747131.pdf?arnumber=9747131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:10:19Z","timestamp":1660594219000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747131\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747131","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}