{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T11:39:35Z","timestamp":1768995575978,"version":"3.49.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9687921","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"388-394","source":"Crossref","is-referenced-by-count":4,"title":["Comparative Study of Different Tokenization Strategies for Streaming End-to-End ASR"],"prefix":"10.1109","author":[{"given":"Sachin","family":"Singh","sequence":"first","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashutosh","family":"Gupta","sequence":"additional","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aman","family":"Maghan","sequence":"additional","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dhananjaya","family":"Gowda","sequence":"additional","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shatrughan","family":"Singh","sequence":"additional","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chanwoo","family":"Kim","sequence":"additional","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"5621","article-title":"Bytes are all you need: End-to-end multilingual speech recog-nition and synthesis with bytes","author":"li","year":"0","journal-title":"ICASSP 2019 — 2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"ref12","first-page":"2130","article-title":"Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model","author":"anjuli","year":"0","journal-title":"Interspeech 2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6451"},{"key":"ref14","first-page":"4960","article-title":"Listen, at-tend and spell: A neural network for large vocabulary conversational speech recognition","author":"chan","year":"0","journal-title":"2016 IEEE In-ternational Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref15","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume":"32","author":"graves","year":"2014","journal-title":"Proceedings of the 31st International Conference on Machine Learning"},{"key":"ref16","author":"graves","year":"2014","journal-title":"Generating Sequences with Recurrent Neural Networks"},{"key":"ref17","article-title":"Investigations on phoneme-based end-to-end speech recognition","author":"zeyer","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref19","article-title":"Training multilingual pre-trained language model with byte-level subwords","volume":"abs 2101 9469","author":"wei","year":"2021","journal-title":"ArXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003936"},{"key":"ref27","article-title":"Streaming end-to-end bilingual asr systems with joint language identification","volume":"abs 2007 3900","author":"punjabi","year":"2020","journal-title":"ArXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref6","article-title":"Multi-task multi-resolution char-to-bpe cross-attention decoder for end-toend speech recognition","author":"gowda","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003976"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref7","article-title":"Streaming on-device end-to-end ASR system for privacy-sensitive voicetyping","author":"garg","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref9","article-title":"End-to-end asr: from supervised to semi-supervised learning with modern architectures","author":"synnaeve","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004027"},{"key":"ref20","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfit-ting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09687921.pdf?arnumber=9687921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:58:27Z","timestamp":1652201907000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687921\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9687921","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}