{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T04:39:29Z","timestamp":1779251969100,"version":"3.51.4"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447494","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11041-11045","source":"Crossref","is-referenced-by-count":5,"title":["Soft Alignment of Modality Space for End-to-End Speech Translation"],"prefix":"10.1109","author":[{"given":"Yuhao","family":"Zhang","sequence":"first","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiqi","family":"Kou","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bei","family":"Li","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Xu","sequence":"additional","affiliation":[{"name":"Harbin Engineering University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingbo","family":"Zhu","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation","volume-title":"Proc. of NIPS Workshop on end-to-end learning for speech and audio processing","author":"B\u00e9rard"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1109"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17509"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.68"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.108"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.663"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1065"},{"key":"ref8","article-title":"Fused acoustic and text encoding for multimodal bilingual pretraining and speech translation","volume-title":"Proc. of ICML","author":"Zheng"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.204"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26637"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1168"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.688"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.376"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.216"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref16","article-title":"Domain-adversarial training of neural networks","author":"Ganin","year":"2016","journal-title":"The journal of machine learning research"},{"key":"ref17","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. of NeurIPS","author":"Baevski"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.486"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.328"},{"key":"ref21","article-title":"Pre-training for speech translation: Ctc meets optimal transport","volume-title":"Proc. of ICML","author":"Le"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref23","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. of ICML","author":"Verma"},{"key":"ref24","article-title":"MuST-C: a Multilingual Speech Translation Corpus","volume-title":"Proc. of NAACL","author":"Di Gangi"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref27","article-title":"Fairseq S2T: Fast speech-to-text modeling with fairseq","volume-title":"Proc. of AACL","author":"Wang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref30","article-title":"Visualizing data using t-sne","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447494.pdf?arnumber=10447494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:43:30Z","timestamp":1722577410000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447494\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447494","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}