{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:05:42Z","timestamp":1730297142472,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022466","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"76-83","source":"Crossref","is-referenced-by-count":0,"title":["Alternate Intermediate Conditioning with Syllable-Level and Character-Level Targets for Japanese ASR"],"prefix":"10.1109","author":[{"given":"Yusuke","family":"Fujita","sequence":"first","affiliation":[{"name":"LINE Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Komatsu","sequence":"additional","affiliation":[{"name":"LINE Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Kida","sequence":"additional","affiliation":[{"name":"LINE Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Attention-based models for speech recognition","volume-title":"Proc. NIPS","author":"Chorowski","key":"ref1"},{"article-title":"Sequence transduction with recurrent neural networks","volume-title":"International Conference on Ma-chine Learning: Representation Learning Workshop","author":"Graves","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3044547"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2404"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.154"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/asru51503.2021.9688157"},{"key":"ref12","first-page":"12449","article-title":"wav2vec 2. 0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","volume":"33","author":"Baevski"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282226"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1118"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953071"},{"key":"ref17","first-page":"485","article-title":"Hierarchical Mul-titask Learning With CTC","volume-title":"Proc. SLT","author":"Sanabria"},{"article-title":"Corpus of spontaneous japanese: Its design and evaluation","volume-title":"ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition","author":"Maekawa","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.149"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054557"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746580"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref25","first-page":"5874","article-title":"Recent developments on es-pnet toolkit boosted by conformer","volume-title":"Proc. ICA SSP","author":"Guo"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-2012"},{"article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. ASRU","author":"Povey","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"article-title":"Adam: A Method for Stochastic Optimization","volume-title":"Proc. ICLR","author":"Kingma","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688137"},{"key":"ref33","article-title":"Improving ctc-based asr models with gated interlayer collaboration","volume":"abs\/2205. 12462","author":"Yang","year":"2022","journal-title":"ArXiv"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022466.pdf?arnumber=10022466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:33:22Z","timestamp":1707813202000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022466\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022466","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}