{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:49:15Z","timestamp":1777060155362,"version":"3.51.4"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832134","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Temporal Order Preserved Optimal Transport-Based Cross-Modal Knowledge Transfer Learning for 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","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p17-1048"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1211.3711"},{"key":"ref7","first-page":"1081","article-title":"Effective sentence scoring method using BERT for speech recognition","volume-title":"Proc. of ACML","author":"Shin"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"ref9","first-page":"17641772","article-title":"Towards end to-end speech recognition with recurrent neural networks","volume-title":"Proc. ICML","author":"Graves"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746580"},{"key":"ref11","article-title":"Multi-sequence intermediate conditioning for ctc-based asr","author":"Fujita","year":"2022","journal-title":"arXiv preprint, arXiv:2204.00175"},{"key":"ref12","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint, arXiv:1810.04805"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3082299"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3166400"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746801"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-716"},{"key":"ref17","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. of NeurIPS","author":"Baevski"},{"key":"ref18","article-title":"Distilling the Knowledge of BERT for CTC-based ASR","author":"Futami","year":"2022","journal-title":"CoRR abs\/2209.02030"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095186"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-423"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022825"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747887"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746316"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447838"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747101"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","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":"ref28","first-page":"3733","article-title":"Joint distribution optimal transportation for domain adaptation","volume-title":"Proc. of NIPS","author":"Courty"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414045"},{"key":"ref30","first-page":"19935","article-title":"Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport","volume-title":"Proc. of NeurIPS","author":"Lin"},{"key":"ref31","article-title":"Interpretations of Domain Adaptations via Layer Variational Analysis","author":"Tseng","year":"2023","journal-title":"arXiv preprint, CoRR abs\/2302.01798"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1246"},{"key":"ref33","first-page":"78027806","article-title":"Optimizing Alignment of Speech and Language Latent Spaces for End-To-End Speech Recognition and Understanding","volume-title":"Proc. of ICASSP","author":"Wang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.436"},{"key":"ref35","volume-title":"Pre-training for Speech Translation: CTC Meets Optimal Transport","author":"Le","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389680"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref38","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. of NIPS","volume":"26","author":"Cuturi"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.310"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref42","article-title":"Adam: A Method for Stochastic Optimization","volume-title":"Proc. of ICLR","author":"Diederik"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-483"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832134.pdf?arnumber=10832134","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:49:56Z","timestamp":1737100196000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832134\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832134","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}