{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:38:42Z","timestamp":1783183122979,"version":"3.54.6"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171470"],"award-info":[{"award-number":["62171470"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276153"],"award-info":[{"award-number":["62276153"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Central Plains Science and Technology Innovation Leading Talent Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3244521","type":"journal-article","created":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T18:58:17Z","timestamp":1677524297000},"page":"1075-1086","source":"Crossref","is-referenced-by-count":15,"title":["Improving Speech Translation by Cross-Modal Multi-Grained Contrastive Learning"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8852-6311","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"first","affiliation":[{"name":"School of the Information Engineering University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nianwen","family":"Si","sequence":"additional","affiliation":[{"name":"School of the Information Engineering University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6301-802X","authenticated-orcid":false,"given":"Yaqi","family":"Chen","sequence":"additional","affiliation":[{"name":"School of the Information Engineering University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenlin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of the Information Engineering University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7989-7089","authenticated-orcid":false,"given":"Xukui","family":"Yang","sequence":"additional","affiliation":[{"name":"School of the Information Engineering University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9917-7794","authenticated-orcid":false,"given":"Dan","family":"Qu","sequence":"additional","affiliation":[{"name":"School of the Information Engineering University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3841-1959","authenticated-orcid":false,"given":"Wei-Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758176"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660082"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00270"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2582"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17509"},{"key":"ref7","article-title":"Bridging the modality gap for speech-to-text translation","author":"Liu","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21303"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.486"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1065"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.204"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.195"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.328"},{"key":"ref14","first-page":"1","article-title":"Listen and translate: A proof of concept for end-to-end speech-to-text translation","volume-title":"Proc. NIPS Workshop End-to-End Learn. Speech Audio Process.","author":"Brard","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1109"},{"key":"ref16","first-page":"1","article-title":"Augmenting librispeech with french translations: A multimodal corpus for direct speech translation evaluation","volume-title":"Proc. 11th Int. Conf. Lang. Resour. Eval.","author":"Kocabiyikoglu","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683343"},{"key":"ref18","article-title":"Harnessing indirect training data for end-to-end automatic speech translation: Tricks of the trade","volume-title":"Proc. 16th Int. Conf. Spoken Lang. Transl.","author":"Pino","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6360"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1006"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053847"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.344"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.108"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.105"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2938"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9054759"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.393"},{"key":"ref32","first-page":"11712","article-title":"Frequency-aware contrastive learning for neural machine translation","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Ye","year":"2022"},{"key":"ref33","article-title":"Multi-format contrastive learning of audio representations","author":"Wang","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-022-02075-7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414079"},{"key":"ref36","first-page":"25","article-title":"Self-supervised multimodal versatile networks","volume":"33","author":"Alayrac","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.376"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref41","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zeng","year":"2022"},{"key":"ref42","first-page":"51","article-title":"Fine-grained multi-modal self-supervised learning","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Wang","year":"2021"},{"key":"ref43","article-title":"Unist: Unified end-to-end model for streaming and non-streaming speech translation","author":"Dong","year":"2021"},{"key":"ref44","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.733"},{"key":"ref46","first-page":"1","article-title":"Representation degeneration problem in training natural language generation models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gao","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.248"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.23"},{"key":"ref49","article-title":"Whitening sentence representations for better semantics and faster retrieval","author":"Su","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3140693"},{"key":"ref53","first-page":"2012","article-title":"Must-C: A multilingual speech translation corpus","volume-title":"Proc. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Gangi","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref57","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref58","doi-asserted-by":"crossref","first-page":"302","DOI":"10.18653\/v1\/2020.acl-demos.34","article-title":"ESPnet-ST: All-in-one speech translation toolkit","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics: Syst. Demonstrations","author":"Inaguma","year":"2020"},{"key":"ref59","first-page":"186","article-title":"A call for clarity in reporting BLEU scores","volume-title":"Proc. 3rd Conf. Mach. Transl.: Res. Papers","author":"Post","year":"2018"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.230"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.314"},{"key":"ref62","article-title":"Linear interpolation in parameter space is good enough for fine-tuned language models","author":"Rofin","year":"2022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"ref65","article-title":"Improving neural machine translation by denoising training","author":"Ding","year":"2022"},{"key":"ref66","first-page":"1","article-title":"Hallucinations in neural machine translation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","year":"2019"},{"key":"ref67","first-page":"1","article-title":"SVCCA: Singular vector canonical correlation analysis for deep learning dynamics and interpretability","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Raghu","year":"2017"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.17"},{"key":"ref69","first-page":"1","article-title":"Insights on representational similarity in neural networks with canonical correlation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Morcos","year":"2018"},{"issue":"11","key":"ref70","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10042965.pdf?arnumber=10042965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T13:05:16Z","timestamp":1707829516000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10042965\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3244521","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}