{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:07:43Z","timestamp":1725808063206},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414212","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"5659-5663","source":"Crossref","is-referenced-by-count":13,"title":["Less is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging"],"prefix":"10.1109","author":[{"given":"Rohit","family":"Prabhavalkar","sequence":"first","affiliation":[]},{"given":"Yanzhang","family":"He","sequence":"additional","affiliation":[]},{"given":"David","family":"Rybach","sequence":"additional","affiliation":[]},{"given":"Sean","family":"Campbell","sequence":"additional","affiliation":[]},{"given":"Arun","family":"Narayanan","sequence":"additional","affiliation":[]},{"given":"Trevor","family":"Strohman","sequence":"additional","affiliation":[]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Adam: A Method for Stochastic Optimization","year":"2014","author":"kingma","key":"ref38"},{"key":"ref33","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":"Proc of Interspeech"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053205"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref36","article-title":"Tensorflow: A System for Large-Scale Machine Learning","author":"abadi","year":"2016","journal-title":"Proc of Symposium on Operating Systems"},{"article-title":"Lingvo: A Modular and Scalable Framework for Sequence-to-Sequence Modeling","year":"2019","author":"shen","key":"ref35"},{"key":"ref34","article-title":"Improving wideband speech rcognition using mixed-bandwidth training data in cd-dnn-hmm","author":"li","year":"2012","journal-title":"Proc of SLT"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref13","article-title":"Sequence to Sequence Learning with Neural Networks","author":"sutskever","year":"2014","journal-title":"Proc of NeurIPS"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-343","article-title":"Towards Better Decoding and Language Model Integration in Sequence to Sequence Models","author":"chorowski","year":"2017","journal-title":"Proc of Interspeech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003822"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054419"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref18","article-title":"Attention Is All You Need","author":"vaswani","year":"2017","journal-title":"Proc of NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref3","article-title":"Exploring Architectures, Data and Units for Streaming End-to-End Speech Recognition with RNN-Transducer","author":"rao","year":"2017","journal-title":"Proc of ASRU"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref5","article-title":"Attention-Based Models for Speech Recognition","author":"chorowski","year":"2015","journal-title":"Proc of NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/79.382443"},{"article-title":"Transformer-Transducer: End-to-End Speech Recognition with SelfAttention","year":"2019","author":"yeh","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"article-title":"Sequence Transduction with Recurrent Neural Networks","year":"2012","author":"graves","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854535"},{"key":"ref22","article-title":"Rapid and Accurate Spoken Term Detection","author":"miller","year":"2007","journal-title":"Proc of Interspeech"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2667"},{"key":"ref24","article-title":"Estimating Confidence using Word Lattices","author":"kemp","year":"1997","journal-title":"Proc of European Conference on Speech Communication and Technology"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.918413"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1557"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461809"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414212.pdf?arnumber=9414212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:06Z","timestamp":1652197266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414212\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414212","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}