{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:37:54Z","timestamp":1753601874637,"version":"3.28.0"},"reference-count":22,"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\/asru57964.2023.10389787","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:40Z","timestamp":1705671520000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Discriminative Speech Recognition Rescoring With Pre-Trained Language Models"],"prefix":"10.1109","author":[{"given":"Prashanth Gurunath","family":"Shivakumar","sequence":"first","affiliation":[{"name":"Amazon Alexa AI,USA"}]},{"given":"Jari","family":"Kolehmainen","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI,USA"}]},{"given":"Yile","family":"Gu","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI,USA"}]},{"given":"Ankur","family":"Gandhe","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI,USA"}]},{"given":"Ariya","family":"Rastrow","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI,USA"}]},{"given":"Ivan","family":"Bulyko","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI,USA"}]}],"member":"263","reference":[{"article-title":"An empirical study of efficient asr rescoring with transformers","volume-title":"arXiv preprint arXiv:1910.11450","author":"Huang","key":"ref1"},{"key":"ref2","first-page":"1081","article-title":"Effective sentence scoring method using bert for speech recognition","volume-title":"Asian Conference on Machine Learning","author":"Shin"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11123"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747118"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096429"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1981"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-990"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2128"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461809"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472827"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054335"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383497"},{"key":"ref15","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in neural information processing systems","volume":"33","author":"Brown"},{"article-title":"Scaling laws for neural language models","volume-title":"arXiv preprint arXiv:2001.08361","author":"Kaplan","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.459"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"arXiv preprint arXiv:2212.04356","author":"Radford","key":"ref19"},{"key":"ref20","article-title":"Attention is all you need","volume-title":"Advances in neural information processing systems","volume":"30","author":"Vaswani"},{"issue":"8","key":"ref21","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume-title":"OpenAI blog","volume":"1","author":"Radford"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"arXiv preprint arXiv:1810.04805","author":"Devlin","key":"ref22"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","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\/10389787.pdf?arnumber=10389787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T11:30:43Z","timestamp":1706009443000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389787\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389787","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}