{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:08:32Z","timestamp":1755839312048,"version":"3.37.3"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020962","name":"ACT-X","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020962","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746580","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7797-7801","source":"Crossref","is-referenced-by-count":16,"title":["Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units"],"prefix":"10.1109","author":[{"given":"Yosuke","family":"Higuchi","sequence":"first","affiliation":[{"name":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keita","family":"Karube","sequence":"additional","affiliation":[{"name":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuji","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsunori","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.154"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1975"},{"article-title":"On the inductive bias of word-character-level multi-task learning for speech recognition","year":"2018","author":"kremer","key":"ref32"},{"key":"ref31","first-page":"111","article-title":"Acoustic-to-word model without OOV","author":"li","year":"2017","journal-title":"Proc ASRU"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953069"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414911"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1866"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1171"},{"key":"ref27","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref2","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc NeurIPS"},{"key":"ref1","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc ICML"},{"key":"ref20","first-page":"774","article-title":"Sequence labelling in structured domains with hierarchical recurrent neural networks","author":"fern\u00e1ndez","year":"2007","journal-title":"Proc IJ-CAI"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1118","article-title":"Multitask learning with low-level auxiliary tasks for encoder-decoder based speech recognition","author":"toshniwal","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953071"},{"article-title":"Hierarchical multitask learning for CTC-based speech recognition","year":"2018","author":"krishna","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639530"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052964"},{"article-title":"Citrinet: Closing the gap between non-autoregressive and autoregressive end-to-end models for automatic speech recognition","year":"2021","author":"majumdar","key":"ref10"},{"key":"ref40","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 of LREC"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"ref13","first-page":"449","article-title":"A comparative study on Transformer vs RNN in speech applications","author":"karita","year":"2019","journal-title":"Proc ASRU"},{"key":"ref14","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proc ECCV"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","year":"2020","author":"zhang","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2225"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1976.10159"},{"article-title":"Neural speech recognizer: Acoustic-to-word LSTM model for large vocabulary speech recognition","year":"2016","author":"soltau","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref6","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc NeurIPS"},{"article-title":"Sequence transduction with recurrent neural networks","year":"2012","author":"graves","key":"ref5"},{"key":"ref8","first-page":"5884","article-title":"Speech-Transformer: A no-recurrence sequence-to-sequence model for speech recognition","author":"dong","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1623"},{"key":"ref7","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"Proc ICLR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688157"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-337"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682494"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2404"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref41","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746580.pdf?arnumber=9746580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:11:38Z","timestamp":1660594298000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746580\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746580","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}