{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:16Z","timestamp":1775230096564,"version":"3.50.1"},"reference-count":30,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887892","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Token-Level Contextual Network with Ladder-Shaped Attention for End-to-End ASR"],"prefix":"10.1109","author":[{"given":"Ming","family":"Fang","sequence":"first","affiliation":[{"name":"Ping An Technology,Shenzhen,China"}]},{"given":"Kai","family":"Guo","sequence":"additional","affiliation":[{"name":"Ping An Technology,Shenzhen,China"}]},{"given":"Tao","family":"Wei","sequence":"additional","affiliation":[{"name":"Ping An Technology,Shenzhen,China"}]},{"given":"Ziyang","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Ping An Technology,Shenzhen,China"}]},{"given":"Yan","family":"Shi","sequence":"additional","affiliation":[{"name":"Ping An Technology,Shenzhen,China"}]},{"given":"Ning","family":"Cheng","sequence":"additional","affiliation":[{"name":"Ping An Technology,Shenzhen,China"}]},{"given":"Shaojun","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology,Shenzhen,China"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology,Shenzhen,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"International conference on machine learning","author":"Amodei"},{"key":"ref3","article-title":"Attention-based models for speech recognition","author":"Chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref5","article-title":"Sequence transduction with recurrent neural networks","volume-title":"Representation learning workshop, ICML","author":"Graves"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414784"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003790"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383515"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1209"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383560"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1566"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1434"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687915"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415054"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022705"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687895"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-767"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389732"},{"key":"ref24","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-483"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747101"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1171"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref30","author":"Du","year":"2018","journal-title":"Aishell-2: Transforming mandarin asr research into industrial scale"}],"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\/10887892.pdf?arnumber=10887892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:10Z","timestamp":1774416370000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887892\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887892","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}