{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T12:36:02Z","timestamp":1777638962304,"version":"3.51.4"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892941","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Effective Cross-Utterance Language Modeling for Conversational Speech Recognition"],"prefix":"10.1109","author":[{"given":"Bi-Cheng","family":"Yan","sequence":"first","affiliation":[{"name":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsin-Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shih-Hsuan","family":"Chiu","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsuan-Sheng","family":"Chiu","sequence":"additional","affiliation":[{"name":"Chunghwa Telecom Laboratories,Taoyuan,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Berlin","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University,Department of Computer Science and Information Engineering,Taipei,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref32","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref30","first-page":"2207","article-title":"ESPnet: End-to-end speech processing toolkit","author":"watanabe","year":"2019","journal-title":"Proceedings of the Annual Conference of the International Speech Communication Association (Interspeech)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.265"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1716"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1027"},{"key":"ref13","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional Transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies (NAACL-HLT)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-65"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1164"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383557"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533796"},{"key":"ref19","article-title":"Cross-utterance reranking models with BERT and graph convolutional networks for conversational speech recognition","author":"chiu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-332"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1296"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1242"},{"key":"ref3","first-page":"3246","article-title":"Adapting long Ccontext NLM for ASR rescoring in conversational agents","author":"shenoy","year":"2021","journal-title":"Proceedings of the Annual Conference of the International Speech Communication Association (Interspeech)"},{"key":"ref6","article-title":"Improving neural language models with a continuous cache","author":"grave","year":"2017","journal-title":"Proceedings of International Conference on Learning Representations (ICLR)"},{"key":"ref29","first-page":"28","article-title":"The AMI meeting corpus: A pre-announcement","author":"carletta","year":"2005","journal-title":"Proceedings of the International Workshop on Machine Learning for Multimodal Interaction"},{"key":"ref5","first-page":"2949","article-title":"A discourse-aware graph neural network for emotion recognition in multi-party conversation","author":"yang","year":"2021","journal-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414477"},{"key":"ref7","article-title":"Dynamic evaluation of transformer language models","author":"krause","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref1","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"ravanelli","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1784"},{"key":"ref21","first-page":"1081","article-title":"Effective sentence scoring method using BERT for speech recognition","author":"shin","year":"2019","journal-title":"Proceedings of The Asian Conference on Machine Learning (ACML)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1525\/aa.1968.70.6.02a00030"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1037\/0278-7393.22.6.1482"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.236"},{"key":"ref25","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","location":"Padua, Italy","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892941.pdf?arnumber=9892941","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:59:55Z","timestamp":1667516395000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892941\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892941","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}