{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:55:12Z","timestamp":1774367712287,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096744","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Robust Knowledge Distillation from RNN-T Models with Noisy Training Labels Using Full-Sum Loss"],"prefix":"10.1109","author":[{"given":"Mohammad","family":"Zeineldeen","sequence":"first","affiliation":[{"name":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52074"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kartik","family":"Audhkhasi","sequence":"additional","affiliation":[{"name":"Google LLC,New York"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murali Karthick","family":"Baskar","sequence":"additional","affiliation":[{"name":"Google LLC,New York"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[{"name":"Google LLC,New York"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Speechstew: Simply mix all available speech recognition data to train one large neural network","author":"chan","year":"2021","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413905"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1510","article-title":"Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in Google Home","author":"kim","year":"2017","journal-title":"InterSpeech"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639699"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461995"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1510","article-title":"Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in google home","author":"kim","year":"2017","journal-title":"InterSpeech"},{"key":"ref2","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"CoRR"},{"key":"ref1","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref16","first-page":"28","article-title":"The AMI meeting corpus: A pre-announcement","author":"carletta","year":"0","journal-title":"MLMI 2005 Edinburgh UK July 11-13 2005 Revised Selected Papers"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref8","author":"hwang","year":"2022"},{"key":"ref7","first-page":"118:1","article-title":"A general framework for adversarial label learning","author":"arachie","year":"2021","journal-title":"J Mach Learn Res"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746168"},{"key":"ref4","article-title":"Deep model compression: Distilling knowledge from noisy teachers","author":"sau","year":"2016","journal-title":"CoRR"},{"key":"ref3","article-title":"Knowledge distillation: Bad models can be good role models","author":"kaplun","year":"2022","journal-title":"CoRR"},{"key":"ref6","first-page":"3183","article-title":"Adversarial label learning","author":"arachie","year":"2019","journal-title":"The Thirty-Third AAAI Conference on Artificial Intelligence AAAI 2019 The Thirty-First Innovative Applications of Artificial Intelligence Conference IAAI 2019 The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence EAAI 2019 Honolulu Hawaii USA January 27 - February 1 2019"},{"key":"ref5","article-title":"Does label smoothing mitigate label noise?","author":"lukasik","year":"2020","journal-title":"ICML"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096744.pdf?arnumber=10096744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:02:52Z","timestamp":1700506972000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096744\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096744","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}