{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:12:54Z","timestamp":1753600374383},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054335","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"7944-7948","source":"Crossref","is-referenced-by-count":16,"title":["Audio-Attention Discriminative Language Model for ASR Rescoring"],"prefix":"10.1109","author":[{"given":"Ankur","family":"Gandhe","sequence":"first","affiliation":[]},{"given":"Ariya","family":"Rastrow","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"939","DOI":"10.21437\/Interspeech.2017-233","article-title":"A comparison of sequence-to-sequence models for speech recognition","author":"prabhavalkar","year":"2017","journal-title":"InterSpeech"},{"key":"ref11","article-title":"Cold fusion: Training seq2seq models together with language models","author":"sriram","year":"2017","journal-title":"CoRR"},{"key":"ref12","first-page":"1","article-title":"An analysis of incorporating an external language model into a sequence-to-sequence model","author":"kannan","year":"2018","journal-title":"2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1209"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1109\/SLT.2018.8639034","article-title":"Deep context: end-to-end contextual speech recognition","author":"pundak","year":"2018","journal-title":"Proceedings of 2018 IEEE Spoken Language Technology Workshop (SLT)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682441"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472827"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683745"},{"key":"ref18","article-title":"Two-pass end-to-end speech recognition","author":"chiu","year":"2019","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854535"},{"key":"ref3","article-title":"Lstm neural networks for language modeling","author":"sundermeyer","year":"2012","journal-title":"Thirteenth Annual Conference of the International Speech Communication Association"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3060"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268931"},{"key":"ref8","article-title":"Listen, attend and spell","author":"chan","year":"2015","journal-title":"arXiv preprint arXiv 1508 01211"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref2","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Eleventh Annual Conference of the International Speech Communication Association"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-234","article-title":"Acoustic modeling for google home","author":"li","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2013-548","article-title":"Sequence-discriminative training of deep neural networks","author":"vesely??","year":"2013"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref23","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054335.pdf?arnumber=9054335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T15:27:24Z","timestamp":1696001244000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054335\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054335","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}