{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T04:52:19Z","timestamp":1769921539607,"version":"3.49.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053159","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"8069-8073","source":"Crossref","is-referenced-by-count":24,"title":["Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection"],"prefix":"10.1109","author":[{"given":"Qian","family":"Chen","sequence":"first","affiliation":[]},{"given":"Mengzhe","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[]},{"given":"Wen","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Text chunking using transformation-based learning","author":"ramshaw","year":"1995","journal-title":"VLC ACL"},{"key":"ref32","article-title":"Hybrid self-attention network for machine translation","volume":"abs 1811 253","author":"song","year":"2018","journal-title":"CoRR"},{"key":"ref31","first-page":"5446","article-title":"Disan: Directional self-attention network for rnn\/cnn-free language understanding","author":"shen","year":"2018","journal-title":"AAAI"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.02.003"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","volume":"abs 1412 6980","author":"kingma","year":"2014","journal-title":"CoRR"},{"key":"ref34","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1517"},{"key":"ref11","first-page":"1526","article-title":"Enriching speech recognition with automatic detection of sentence boundaries and disfluencies","volume":"14","author":"liu","year":"2006","journal-title":"IEEE TASLP"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.675358"},{"key":"ref13","article-title":"Punctuation annotation using statistical prosody models","author":"christensen","year":"2001","journal-title":"ITRW"},{"key":"ref14","first-page":"3097","article-title":"Improved models for automatic punctuation prediction for spoken and written text","author":"ueffing","year":"2013","journal-title":"InterSpeech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1096"},{"key":"ref16","first-page":"177","article-title":"Better punctuation prediction with dynamic conditional random fields","author":"lu","year":"2010","journal-title":"EMNLP"},{"key":"ref17","article-title":"Punctuation prediction for unsegmented transcript based on word vector","author":"che","year":"2016","journal-title":"LREC"},{"key":"ref18","first-page":"683","article-title":"LSTM for punctuation restoration in speech transcripts","author":"tilk","year":"2015","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1079"},{"key":"ref28","first-page":"124","article-title":"Joint parsing and disfluency detection in linear time","author":"rasooli","year":"2013","journal-title":"EMNLP"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1013"},{"key":"ref27","first-page":"547","article-title":"Disfluency detection using a noisy channel model and a deep neural language model","author":"lou","year":"2017","journal-title":"ACL"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016351"},{"key":"ref6","first-page":"4929","article-title":"Deep semantic role labeling with self-attention","author":"tan","year":"2018","journal-title":"AAAI"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1109"},{"key":"ref5","article-title":"Automatic punctuation and disfluency detection in multi-party meetings using prosodic and lexical cues","author":"baron","year":"2002","journal-title":"ICSLP"},{"key":"ref8","article-title":"Punctuation insertion for real-time spoken language translation","author":"cho","year":"2015","journal-title":"IWSLT"},{"key":"ref7","first-page":"252","article-title":"Segmentation and punctuation prediction in speech language translation using a monolingual translation system","author":"cho","year":"2012","journal-title":"IWSLT"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682260"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/O-COCOSDA46868.2019.9041202"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1289"},{"key":"ref20","first-page":"238","article-title":"Modeling punctuation prediction as machine translation","author":"peitz","year":"2011","journal-title":"IWSLT"},{"key":"ref22","first-page":"2624","article-title":"A sequential repetition model for improved disfluency detection","author":"ostendorf","year":"2013","journal-title":"InterSpeech"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846300"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/1620853.1620885"},{"key":"ref23","first-page":"849","article-title":"Recurrent neural networks for incremental disfluency detection","author":"hough","year":"2015","journal-title":"InterSpeech"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1218960"},{"key":"ref25","article-title":"Multi-task self-supervised learning for disfluency detection","volume":"abs 1908 5378","author":"wang","year":"2019","journal-title":"CoRR"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053159.pdf?arnumber=9053159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:19:11Z","timestamp":1656375551000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053159\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053159","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}