{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:34Z","timestamp":1775230114926,"version":"3.50.1"},"reference-count":31,"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\/icassp39728.2021.9414858","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"5874-5878","source":"Crossref","is-referenced-by-count":128,"title":["Recent Developments on Espnet Toolkit Boosted By Conformer"],"prefix":"10.1109","author":[{"given":"Pengcheng","family":"Guo","sequence":"first","affiliation":[]},{"given":"Florian","family":"Boyer","sequence":"additional","affiliation":[]},{"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Tomoki","family":"Hayashi","sequence":"additional","affiliation":[]},{"given":"Yosuke","family":"Higuchi","sequence":"additional","affiliation":[]},{"given":"Hirofumi","family":"Inaguma","sequence":"additional","affiliation":[]},{"given":"Naoyuki","family":"Kamo","sequence":"additional","affiliation":[]},{"given":"Chenda","family":"Li","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Garcia-Romero","sequence":"additional","affiliation":[]},{"given":"Jiatong","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[]},{"given":"Kun","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Wangyou","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yuekai","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1176"},{"key":"ref12","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"Proc ICLR"},{"key":"ref13","article-title":"Efficient Transformers: A survey","author":"tay","year":"2020"},{"key":"ref14","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc ICML"},{"key":"ref15","article-title":"Understanding and improving Transformer from a multi-particle dynamic system point of view","author":"lu","year":"2020","journal-title":"Proc ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639693"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref4","first-page":"5884","article-title":"Speech-Transformer: A norecurrence sequence-to-sequence model for speech recognition","author":"dong","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref2","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"Proc ACL"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.34"},{"key":"ref1","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref22","article-title":"FastSpeech 2: Fast and high-quality end-to-end text-to-speech","author":"ren","year":"2020"},{"key":"ref21","first-page":"3171","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref24","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref23","article-title":"Fastpitch: Parallel text-to-speech with pitch prediction","author":"l\u00e1ncucki","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref25","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Proc INTERSPEECH"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"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\/09414858.pdf?arnumber=9414858","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:00Z","timestamp":1652197260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414858\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414858","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}