{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:29:03Z","timestamp":1774420143069,"version":"3.50.1"},"reference-count":33,"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\/icassp49660.2025.10890819","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["AMuSE: Attentive Multilingual Speech Encoding for Zero-Prior ASR"],"prefix":"10.1109","author":[{"given":"Ashutosh","family":"Varshney","sequence":"first","affiliation":[{"name":"Amazon AGI,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Debmalya","family":"Chakrabarty","sequence":"additional","affiliation":[{"name":"Amazon AGI,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akshat","family":"Jaiswal","sequence":"additional","affiliation":[{"name":"Amazon AGI,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harish","family":"Arsikere","sequence":"additional","affiliation":[{"name":"Amazon AGI,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Jain","sequence":"additional","affiliation":[{"name":"Amazon AGI,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swayambhu Nath","family":"Ray","sequence":"additional","affiliation":[{"name":"Amazon AGI,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frederick","family":"Weber","sequence":"additional","affiliation":[{"name":"Amazon AGI,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anand","family":"Mohan","sequence":"additional","affiliation":[{"name":"Amazon AGI,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prantik","family":"Sen","sequence":"additional","affiliation":[{"name":"Amazon AGI,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Garima","family":"Lalwani","sequence":"additional","affiliation":[{"name":"Amazon AGI,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sambuddha","family":"Bhattacharya","sequence":"additional","affiliation":[{"name":"Amazon AGI,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sri","family":"Garimella","sequence":"additional","affiliation":[{"name":"Amazon AGI,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447399"},{"issue":"97","key":"ref2","first-page":"1","article-title":"Scaling speech technology to 1,000+ languages","volume":"25","author":"Pratap","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11249"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003870"},{"key":"ref5","article-title":"Signal combination for language identification","author":"Wang","year":"2019"},{"key":"ref6","article-title":"Streaming language identification using combination of acoustic representations and asr hypotheses","author":"Chandak","year":"2020"},{"key":"ref7","article-title":"Streaming end-to-end bilingual asr systems with joint language identification","author":"Punjabi","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2292"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-480"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096227"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-478"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414379"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747905"},{"key":"ref14","article-title":"Sequence transduction with recurrent neural networks","author":"Graves","year":"2012"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8181-6_6"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.541"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d15-1166"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-40498-6_25"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref23","article-title":"Seed-asr: Understanding diverse speech and contexts with llm-based speech recognition","author":"Bai","year":"2024"},{"key":"ref24","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref26","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Ardila"},{"key":"ref27","article-title":"The people\u2019s speech: A large-scale diverse english speech recognition dataset for commercial usage","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks","volume":"1","author":"Galvez"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref29","article-title":"free public domain audiobooks","year":"2024"},{"key":"ref30","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Radford"},{"key":"ref31","article-title":"AWS Transcribe","year":"2024"},{"key":"ref32","article-title":"Universal-1: Robust and accurate multilingual speech-to-text","year":"2024"},{"key":"ref33","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","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\/10890819.pdf?arnumber=10890819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:39Z","timestamp":1774416399000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890819","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}