{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:10:12Z","timestamp":1776885012604,"version":"3.51.2"},"reference-count":32,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448361","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"13306-13310","source":"Crossref","is-referenced-by-count":7,"title":["Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study"],"prefix":"10.1109","author":[{"given":"W.","family":"Ronny Huang","sequence":"first","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cyril","family":"Allauzen","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongzhou","family":"Chen","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kilol","family":"Gupta","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Hu","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Qin","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo-Yiin","family":"Chang","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref4","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095326"},{"key":"ref6","article-title":"Megatron-lm: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019"},{"key":"ref7","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":"ref8","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094796"},{"key":"ref10","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref11","article-title":"Palm 2 technical report","author":"Anil","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"ref13","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096429"},{"issue":"1","key":"ref15","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","article-title":"Palm: Scaling language modeling with pathways","author":"Chowdhery","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3166400"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3082299"},{"key":"ref19","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"CoRR","author":"Devlin","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389732"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref23","first-page":"22964","article-title":"What language model architecture and pre-training objective works best for zero-shot generalization?","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268917"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003854"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383518"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-38"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref29","article-title":"Sparks of artificial general intelligence: Early experiments with gpt-4","author":"Bubeck","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095355"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-491"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-268"}],"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\/10448361.pdf?arnumber=10448361","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:43:07Z","timestamp":1722660187000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448361\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448361","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}