{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T12:34:25Z","timestamp":1783427665185,"version":"3.54.6"},"reference-count":52,"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\/asru57964.2023.10389673","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:40Z","timestamp":1705671520000},"page":"1-8","source":"Crossref","is-referenced-by-count":54,"title":["Generative Speech Recognition Error Correction With Large Language Models and Task-Activating Prompting"],"prefix":"10.1109","author":[{"given":"Chao-Han Huck","family":"Yang","sequence":"first","affiliation":[{"name":"Amazon,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yile","family":"Gu","sequence":"additional","affiliation":[{"name":"Amazon,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Chieh","family":"Liu","sequence":"additional","affiliation":[{"name":"Amazon,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shalini","family":"Ghosh","sequence":"additional","affiliation":[{"name":"Amazon,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Bulyko","sequence":"additional","affiliation":[{"name":"Amazon,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Stolcke","sequence":"additional","affiliation":[{"name":"Amazon,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.759"},{"key":"ref3","article-title":"Finetuned language models are zero-shot learners","volume-title":"Proc. ICLR","author":"Wei"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.175"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref6","article-title":"Hyporadise: An open baseline for generative speech recognition with large language models","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383560"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683745"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3557894"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-660"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1616"},{"key":"ref12","article-title":"Multitask prompted training enables zero-shot task generalization","author":"Sanh","year":"2021","journal-title":"arXiv preprint arXiv:2110.08207"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.244"},{"key":"ref14","article-title":"Why can GPT learn in-context? language models implicitly perform gradient descent as meta-optimizers","volume-title":"Proc. ICLR Workshop on Mathematical and Empirical Understanding of Foundation Models","author":"Dai"},{"key":"ref15","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"NeurIPS"},{"key":"ref16","article-title":"Large language models are zero-shot reasoners","author":"Kojima","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","article-title":"An explanation of in-context learning as implicit bayesian inference","author":"Xie","year":"2021","journal-title":"Proc. ICLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.32.5.1276"},{"key":"ref19","article-title":"Impact of pretraining term frequencies on few-shot reasoning","author":"Razeghi","year":"2022","journal-title":"arXiv preprint arXiv:2202.07206"},{"key":"ref20","article-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","volume-title":"Proc. ICLR","author":"Kumar"},{"key":"ref21","first-page":"11 808","article-title":"Voice2Series: Reprogramming acoustic models for time series classification","volume-title":"Proc. International Conference on Machine Learning","author":"Yang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10610"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11031"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.381"},{"key":"ref25","article-title":"Explanation selection using unlabeled data for in-context learning","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv:2302.04813"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref32","first-page":"12 449","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":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747118"},{"key":"ref34","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461809"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/89.568732"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940763"},{"key":"ref38","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. ICLR","author":"Lan"},{"issue":"8","key":"ref39","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref40","article-title":"BLOOM: A 176b-parameter open-access multilingual language model","author":"Scao","year":"2022","journal-title":"arXiv preprint arXiv:2211.05100"},{"key":"ref41","article-title":"Pointer sentinel mixture models","volume-title":"Proc. ICLR","author":"Merity"},{"key":"ref42","article-title":"A simple method for commonsense reasoning","author":"Trinh","year":"2018","journal-title":"arXiv preprint arXiv:1806.02847"},{"key":"ref43","article-title":"OpenLLaMA: An open reproduction of LLaMA","author":"Geng","year":"2023"},{"key":"ref44","article-title":"RedPajama: An open source recipe to reproduce LLaMA training dataset","author":"Computer","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-demo.21"},{"key":"ref46","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/116580.116613"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21236\/ada273556"},{"key":"ref49","article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.01037"},{"key":"ref50","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"International Conference on Machine Learning","author":"Houlsby"},{"key":"ref51","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"}],"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\/10389673.pdf?arnumber=10389673","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T11:45:53Z","timestamp":1706010353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389673\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389673","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}