{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:08:37Z","timestamp":1725808117084},"reference-count":32,"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\/slt54892.2023.10022760","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"46-51","source":"Crossref","is-referenced-by-count":2,"title":["Interdecoder: using Attention Decoders as Intermediate Regularization for CTC-Based Speech Recognition"],"prefix":"10.1109","author":[{"given":"Tatsuya","family":"Komatsu","sequence":"first","affiliation":[{"name":"LINE Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Fujita","sequence":"additional","affiliation":[{"name":"LINE Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref4","first-page":"5874","article-title":"Recent developments on es-pnet toolkit boosted by conformer","volume-title":"Proc. ICASSP","author":"Guo"},{"key":"ref5","first-page":"369","article-title":"Connectionist temporal classifi-cation: Labelling unsegmented sequence data with re-current neural networks","volume-title":"Proc. ICML","author":"Graves"},{"key":"ref6","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"Proc. ICML","author":"Amodei"},{"article-title":"Attention-based models for speech recognition","volume-title":"Proc. NIPS","author":"Chorowski","key":"ref7"},{"article-title":"Sequence transduction with recurrent neural networks","volume-title":"Proc. ICML: Representation Learning Workshop","author":"Graves","key":"ref8"},{"key":"ref9","first-page":"1403","article-title":"Imputer: Sequence modelling via imputation and dynamic program-ming","volume-title":"Proc. ICML","author":"Chan"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3044547"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2404"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.154"},{"key":"ref13","first-page":"6224","article-title":"Intermediate loss regularization for etc-based speech recognition","volume-title":"Proc. ICASSP","author":"Lee"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref15","first-page":"7797","article-title":"Hierarchical conditional end-to-end asr with etc and multi-granular subword units","volume-title":"Proc. ICASSP","author":"Higuchi"},{"key":"ref16","article-title":"Improving etc-based asr models with gated interlayer collaboration","author":"Yang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11284"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1118"},{"key":"ref19","first-page":"485","article-title":"Hierarchical mul-titask learning with etc","volume-title":"Proc. SLT","author":"Sanabria"},{"key":"ref20","article-title":"Hierarchical multitask learning for etc-based speech recognition","author":"Krishna","year":"2018","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688157"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052964"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","first-page":"3935","article-title":"Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks","author":"Rousseau","year":"2014","journal-title":"Porc. LREC"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P18-1007","article-title":"Subword regularization: Improving neural network translation models with multiple subword can-didates","volume-title":"Proc. ACL","author":"Kudo"},{"article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. ASRU","author":"Povey","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref31","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":"ref32"}],"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\/10022760.pdf?arnumber=10022760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:10:31Z","timestamp":1707804631000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022760\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022760","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}