{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T14:22:55Z","timestamp":1773325375670,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746863","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7567-7571","source":"Crossref","is-referenced-by-count":12,"title":["Temporal Early Exiting for Streaming Speech Commands Recognition"],"prefix":"10.1109","author":[{"given":"Raphael","family":"Tang","sequence":"first","affiliation":[{"name":"Comcast Applied AI"}]},{"given":"Karun","family":"Kumar","sequence":"additional","affiliation":[{"name":"Comcast Applied AI"}]},{"given":"Ji","family":"Xin","sequence":"additional","affiliation":[{"name":"University of Waterloo"}]},{"given":"Piyush","family":"Vyas","sequence":"additional","affiliation":[{"name":"Comcast Applied AI"}]},{"given":"Wenyan","family":"Li","sequence":"additional","affiliation":[{"name":"Comcast Applied AI"}]},{"given":"Gefei","family":"Yang","sequence":"additional","affiliation":[{"name":"Comcast Applied AI"}]},{"given":"Yajie","family":"Mao","sequence":"additional","affiliation":[{"name":"Comcast Applied AI"}]},{"given":"Craig","family":"Murray","sequence":"additional","affiliation":[{"name":"Comcast Applied AI"}]},{"given":"Jimmy","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Waterloo"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2891838"},{"key":"ref11","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"warden","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.nlposs-1.9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401241"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331271"},{"key":"ref15","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref16","article-title":"MUSAN: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3087"},{"key":"ref18","article-title":"A neural attention model for speech command recognition","author":"de andrade","year":"2018"},{"key":"ref19","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proceedings of AISTATS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683305"},{"key":"ref6","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"Proceedings of the NIPS 2014 Workshop on Deep Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.204"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref1","author":"yu","year":"2014","journal-title":"Automatic Speech Recognition?A Deep Learning Approach"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107392"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal Forced Aligner: Trainable text-speech alignment using Kaldi","author":"mcauliffe","year":"2017","journal-title":"Proceedings of Interspeech"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054240"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683474"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.68"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746863.pdf?arnumber=9746863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:09:54Z","timestamp":1661198994000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746863\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746863","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}