{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:15:14Z","timestamp":1771964114530,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682674","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"5621-5625","source":"Crossref","is-referenced-by-count":74,"title":["Bytes Are All You Need: End-to-end Multilingual Speech Recognition and Synthesis with Bytes"],"prefix":"10.1109","author":[{"given":"Bo","family":"Li","sequence":"first","affiliation":[]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Tara","family":"Sainath","sequence":"additional","affiliation":[]},{"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[]},{"given":"William","family":"Chan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1510","article-title":"Generated 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 INTERSPEECH"},{"key":"ref32","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proc ICML"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.4324\/9780203017883"},{"key":"ref30","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"sak","year":"2015","journal-title":"arXiv preprint arXiv 1507 06947"},{"key":"ref34","article-title":"P. 800: Methods for subjective determination of transmission quality","year":"1996","journal-title":"International Telecommunication Union"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-334"},{"key":"ref12","article-title":"Latent Sequence Decompositions","author":"chan","year":"2017","journal-title":"Proc ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref15","article-title":"Exploring Architectures, Data and Units for Streaming End-to-End Speech Recognition with RNN-Transducer","author":"rao","year":"2017","journal-title":"Proc ASRU"},{"key":"ref16","article-title":"Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition","author":"soltau","year":"2016","journal-title":"arXiv 1610 09975"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462017"},{"key":"ref18","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"ICLR Workshop"},{"key":"ref19","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","author":"wang","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref28","article-title":"Neural Machine Translation by Jointly Learning to Align and Translate","author":"bahdanau","year":"2015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.1005872"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178960"},{"key":"ref6","article-title":"A grapheme based speech recognition system for russian","author":"\u00a8","year":"2004","journal-title":"9th Conference Speech and Computer"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-275"},{"key":"ref5","article-title":"Grapheme based speech recognition","author":"killer","year":"2003","journal-title":"Eighth European Conference on Speech Communication and Technology"},{"key":"ref8","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc ICML"},{"key":"ref7","article-title":"Comparing grapheme-based and phoneme-based speech recognition for afrikaans","author":"basson","year":"2012","journal-title":"Proc PRASA"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-011-0050-4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref1","author":"schultz","year":"2006","journal-title":"Multilingual Speech Processing"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1155"},{"key":"ref21","article-title":"A comparison of sequence-to-sequence models for speech recognition","author":"prabhavalkar","year":"2017","journal-title":"Proc Inter-speech"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461886"},{"key":"ref23","article-title":"Byte-level machine reading across morphologically varied languages","author":"kenter","year":"2018","journal-title":"Proc AAAI"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462201"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682674.pdf?arnumber=8682674","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:11:48Z","timestamp":1657854708000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682674\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682674","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}