{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:49:46Z","timestamp":1776883786949,"version":"3.51.2"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890787","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Bridging Modality Gap with Large Speech and Language Models for End-to-End Speech-to-Text Translation"],"prefix":"10.1109","author":[{"given":"Weitai","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simran","family":"Naagar","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongyi","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiwang","family":"Tang","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhua","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lirong","family":"Dai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"949","article-title":"An attentional model for speech translation without transcription","volume-title":"Proc. NAACL","author":"Duong"},{"key":"ref2","article-title":"Listen and translate: A proof of concept for end-to-end speech-to-text translation","volume-title":"NIPS Workshop on end-to-end learning for speech and audio processing","author":"B\u00e9rard"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref4","first-page":"26 193","volume-title":"Revisiting end-to-end speech-to-text translation from scratch","author":"Zhang","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003774"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.344"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687894"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17508"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6360"},{"key":"ref10","first-page":"2619","article-title":"Stacked acoustic-and-textual encoding: Integrating the pre-trained models into speech translation encoders","volume-title":"Proc. ACL2021","author":"Xu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.108"},{"key":"ref12","first-page":"1488","article-title":"Unified speech-text pre-training for speech translation and recognition","volume-title":"Proc. ACL2022","author":"Tang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/761"},{"key":"ref14","article-title":"Findings of the iwslt 2022 evaluation campaign","volume-title":"Proc. IWSLT 2022","author":"Antonios"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.iwslt-1.1","article-title":"Findings of the iwslt 2023 evaluation campaign","volume-title":"Proc. IWSLT 2023","author":"Agrawal"},{"issue":"8","key":"ref16","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref17","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref19","article-title":"Seamlessm4t-massively multilingual & multimodal machine translation","author":"Barrault","year":"2023"},{"key":"ref20","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023"},{"key":"ref21","first-page":"14 760","article-title":"Speech translation with speech foundation models and large language models: What is there and what is missing?","volume-title":"Proc. ACL2024","author":"Gaido"},{"key":"ref22","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref24","first-page":"6976","article-title":"LLaST: Improved end-to-end speech translation system leveraged by large language models","volume-title":"Findings of the Association for Computational Linguistics ACL 2024","author":"Chen"},{"key":"ref25","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.iwslt-1.15"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2024-777","article-title":"Transferable speech-to-text large language model alignment module","author":"Wu","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447553"},{"key":"ref29","article-title":"Tuning large language model for end-to-end speech translation","author":"Zhang","year":"2023"},{"key":"ref30","first-page":"58 312","article-title":"Comsl: a composite speech-language model for end-to-end speech-to-text translation","volume-title":"Proc. NeurIPS2023","author":"Le"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2024-1858","article-title":"Investigating decoder-only large language models for speech-to-text translation","author":"Huang","year":"2024"},{"key":"ref32","article-title":"Speech translation with large language models: An industrial practice","author":"Huang","year":"2023"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.findings-emnlp.263","article-title":"Wavllm: Towards robust and adaptive speech large language model","author":"Hu","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446635"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref37","article-title":"Cross-domain feature selection for language identification","volume-title":"Proc. IJCNLP","author":"Lui"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref40","article-title":"Multilingual translation with extensible multilingual pretraining and finetuning","author":"Tang","year":"2020"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890787.pdf?arnumber=10890787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:07Z","timestamp":1774416367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890787\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890787","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}