{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:19:36Z","timestamp":1776885576458,"version":"3.51.2"},"reference-count":31,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890008","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Zero-resource Speech Translation and Recognition with LLMs"],"prefix":"10.1109","author":[{"given":"Karel","family":"Mundnich","sequence":"first","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Xing","family":"Niu","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Prashant","family":"Mathur","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Srikanth","family":"Ronanki","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Brady","family":"Houston","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Veera Raghavendra","family":"Elluru","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Nilaksh","family":"Das","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Zejiang","family":"Hou","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Goeric","family":"Huybrechts","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Anshu","family":"Bhatia","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Daniel","family":"Garcia-Romero","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Kyu J.","family":"Han","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]},{"given":"Katrin","family":"Kirchhoff","sequence":"additional","affiliation":[{"name":"AWS AI Labs"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3206084"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11031"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447605"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389703"},{"key":"ref5","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023"},{"key":"ref6","article-title":"Gemini: a family of highly capable multimodal models","author":"Anil","year":"2023"},{"key":"ref7","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":"Advances in neural information processing systems"},{"key":"ref8","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.847"},{"key":"ref10","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.354"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10170"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref14","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"ICML","author":"Chiu"},{"key":"ref15","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.891"},{"issue":"1","key":"ref17","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref20","article-title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","author":"Das","year":"2024"},{"key":"ref21","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref22","article-title":"Listen, think, and understand","volume-title":"International Conference on Learning Representations","author":"Gong"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2027"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054626"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447399"},{"key":"ref27","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref31","article-title":"langdetect","author":"Danilk","year":"2024"}],"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\/10890008.pdf?arnumber=10890008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:25Z","timestamp":1774416325000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890008\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890008","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}