{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:46:11Z","timestamp":1776883571247,"version":"3.51.2"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389644","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-7","source":"Crossref","is-referenced-by-count":4,"title":["Improving Multilingual and Code-Switching ASR Using Large Language Model Generated Text"],"prefix":"10.1109","author":[{"given":"Ke","family":"Hu","sequence":"first","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Cheng","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frederick","family":"Liu","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-343"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-206"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094796"},{"key":"ref5","article-title":"SLAM: A unified encoder for speech and language modeling via speech-text joint pre-training","author":"Bapna","year":"2021","journal-title":"arXiv preprint arXiv:2110.10329"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.105"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747555"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022774"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414607"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.calcs-1.7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.245"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096317"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023313"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/533"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683223"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1009"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746594"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1980"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1429"},{"key":"ref21","article-title":"Towards end-to-end code-switching speech recognition","author":"Luo","year":"2018","journal-title":"arXiv preprint arXiv:1810.13091"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-923"},{"key":"ref23","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref24","article-title":"PaLM 2 technical report","volume-title":"arXiv preprint arXiv:2305.10403","author":"Anil","year":"2023"},{"key":"ref25","first-page":"5547","article-title":"GLaM: Efficient scaling of language models with mixture-of-experts","volume-title":"International Conference on Machine Learning","author":"Du"},{"key":"ref26","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2302.13971"},{"key":"ref27","article-title":"Falcon-40B: an open large language model with state-of-the-art performance","author":"Almazrouei","year":"2023"},{"key":"ref28","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Rubenstein","year":"2023","journal-title":"arXiv preprint arXiv:2306.12925"},{"key":"ref29","article-title":"X-LLM: Bootstrapping advanced large language models by treating multi-modalities as foreign languages","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv:2305.04160"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref32","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv:2106.09685"},{"key":"ref33","article-title":"Speechprompt v2: Prompt tuning for speech classification tasks","author":"Chang","year":"2023","journal-title":"arXiv preprint arXiv:2303.00733"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10006"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IALP.2017.8300581"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref37","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref38","article-title":"PaLM: Scaling language modeling with pathways","author":"Chowdhery","year":"2022","journal-title":"arXiv preprint arXiv:2204.02311"},{"key":"ref39","article-title":"Artificial intelligence at google: Our principles","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-480"},{"key":"ref41","article-title":"Sequence transduction with recurrent neural networks","author":"Graves","year":"2012","journal-title":"arXiv preprint arXiv:1211.3711"},{"key":"ref42","article-title":"Google Translate","year":"2023"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389644.pdf?arnumber=10389644","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:35:40Z","timestamp":1706027740000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389644\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389644","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}