{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:16:39Z","timestamp":1774419399576,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889025","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Joint Automatic Speech Recognition And Structure Learning For Better Speech Understanding"],"prefix":"10.1109","author":[{"given":"Jiliang","family":"Hu","sequence":"first","affiliation":[{"name":"Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering,Wuhan,China"}]},{"given":"Zuchao","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China"}]},{"given":"Mengjia","family":"Shen","sequence":"additional","affiliation":[{"name":"Wuhan Second Ship Design and Research Institute,Wuhan,China"}]},{"given":"Haojun","family":"Ai","sequence":"additional","affiliation":[{"name":"Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering,Wuhan,China"}]},{"given":"Sheng","family":"Li","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}]},{"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Wuhan Second Ship Design and Research Institute,Wuhan,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.151"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.53"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2482"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746955"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389655"},{"key":"ref7","article-title":"1spu: 1-step speech processing unit","author":"Singla","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094687"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10094687"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6510"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1192"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016730"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.318"},{"key":"ref14","article-title":"Sparse fuzzy attention for structured sentiment analysis","author":"Peng","year":"2021"},{"key":"ref15","article-title":"Efficient sequence transduction by jointly predicting tokens and durations","author":"Xu","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022399"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.396"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.639"},{"key":"ref19","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref20","article-title":"Batgpt: A bidirectional autoregessive talker from generative pre-trained transformer","author":"Li","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-9996"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.558"},{"key":"ref23","article-title":"Global pointer: Novel efficient span-based approach for named entity recognition","author":"Su","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746137"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.588"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747674"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1428"},{"key":"ref28","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-11067"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054419"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref32","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref33","article-title":"Primewords chinese corpus set 1","year":"2018"},{"key":"ref34","first-page":"4211","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)","author":"Ardila"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref36","first-page":"125","article-title":"Ted-lium: an automatic speech recognition dedicated corpus","volume-title":"LREC","author":"Rousseau"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889025.pdf?arnumber=10889025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:41Z","timestamp":1774416161000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889025","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}