{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T16:33:17Z","timestamp":1758126797075,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447386","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"13116-13120","source":"Crossref","is-referenced-by-count":1,"title":["Hierarchical Cross-Modality Knowledge Transfer with Sinkhorn Attention for CTC-Based ASR"],"prefix":"10.1109","author":[{"given":"Xugang","family":"Lu","sequence":"first","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Shen","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Academia Sinica,Research Center for Information Technology Innovation,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"17641772","article-title":"Towards end to-end speech recognition with recurrent neural networks","volume-title":"Proc. ICML","author":"Graves"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1561\/116.00000050"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/JSTSP.2017.2763455"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/icassp43922.2022.9746580"},{"key":"ref5","first-page":"76","article-title":"Alternate Intermediate Conditioning with Syllable-Level and CharacterLevel Targets for Japanese ASR","volume-title":"Proc. of SLT","author":"Fujita"},{"volume-title":"Proc. of NeurIPS","author":"Baevski","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","key":"ref6"},{"year":"2018","author":"Devlin","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","key":"ref7"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.21437\/Interspeech.2023-423"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICASSP43922.2022.9747887"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.21437\/Interspeech.2020-1246"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/TASLP.2021.3082299"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/slt54892.2023.10022825"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/TASLP.2022.3166400"},{"key":"ref14","first-page":"8512","article-title":"Knowledge Transfer from Large-Scale Pretrained Language Models to EndTo-End Speech Recognizers","volume-title":"Proc. of ICASSP","author":"Kubo"},{"year":"2022","author":"Futami","article-title":"Distilling the Knowledge of BERT for CTC-based ASR","key":"ref15"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.21437\/Interspeech.2022-716"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/icassp49357.2023.10095186"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.7554\/elife.72056"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/ASRU57964.2023.10389680"},{"key":"ref20","first-page":"9438","article-title":"Sparse Sinkhorn Attention","volume-title":"Proc. of ICML","author":"Tay"},{"key":"ref21","first-page":"3515","article-title":"Sinkformers: Transformers with Doubly Stochastic Attention","volume-title":"Proc. of AISTATS","author":"Sander"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-71050-9","volume-title":"Optimal transport: old and new","volume":"338","author":"Villani","year":"2009"},{"key":"ref24","first-page":"1","article-title":"AIShell1: An open-source mandarin speech corpus and a speech recognition baseline","volume-title":"Proc. of COCOSDA","author":"Bu"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.21437\/Interspeech.2020-3015"},{"volume-title":"Proc. of ICLR","author":"Kingma","article-title":"Adam: A Method for Stochastic Optimization","key":"ref26"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447386.pdf?arnumber=10447386","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:37:19Z","timestamp":1722577039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447386\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447386","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}