{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:24:58Z","timestamp":1759332298429},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446985","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11816-11820","source":"Crossref","is-referenced-by-count":5,"title":["Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models"],"prefix":"10.1109","author":[{"given":"Rohit","family":"Prabhavalkar","sequence":"first","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Zhong","family":"Meng","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Weiran","family":"Wang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Adam","family":"Stooke","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Xingyu","family":"Cai","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Yanzhang","family":"He","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Arun","family":"Narayanan","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Dongseong","family":"Hwang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Pedro J.","family":"Moreno","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3328283"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","volume-title":"Proc. ICML","author":"Radford","key":"ref9"},{"article-title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","year":"2023","author":"Zhang","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1887"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"article-title":"Funnel-Transformer: Filtering Out Sequential Redundancy for Efficient Language Processing","volume-title":"Proc. NeurIPS","author":"Dai","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054419"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414212"},{"article-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","volume-title":"Proc. NeurIPS","author":"Baevski","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10791"},{"key":"ref20","article-title":"Massive End-to-End Models for Short Search Queries","author":"Wang","year":"2023","journal-title":"submitted (under review)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389645"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2442"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-287"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00010"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053040"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11034"},{"key":"ref30","article-title":"Google AI Principles"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1465"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1510"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424210"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-212"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"article-title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","volume-title":"Proc. ICML","author":"Shazeer","key":"ref38"},{"article-title":"Lingvo: A Modular and Scalable Framework for Sequence-to-Sequence Modeling","year":"2019","author":"Shen","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461809"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446985.pdf?arnumber=10446985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:28:24Z","timestamp":1722576504000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446985\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446985","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}