{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:19:40Z","timestamp":1772907580963,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100019594","name":"Yanbian University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100019594","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019594","name":"Yanbian University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100019594","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687992","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["SPformer: Hybrid Sequential-Parallel Architectures for Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Mingdong","family":"Yu","sequence":"first","affiliation":[{"name":"Yanbian University,Yanji,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofeng","family":"Jin","sequence":"additional","affiliation":[{"name":"Yanbian University,Yanji,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guirong","family":"Wang","sequence":"additional","affiliation":[{"name":"Yanbian University,Yanji,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Wang","sequence":"additional","affiliation":[{"name":"Yanbian University,Yanji,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Chen","sequence":"additional","affiliation":[{"name":"Yanbian University,Yanji,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref3","first-page":"9361","article-title":"Squeezeformer: An efficient transformer for automatic speech recognition","volume":"35","author":"Kim","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687874"},{"key":"ref5","first-page":"17627","article-title":"Branch-former: Parallel mlp-attention architectures to capture local and global context for speech recognition and understanding","volume-title":"International Conference on Machine Learning","author":"Peng"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022656"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.35111\/17gk-bn40"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/app10196936"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2016.7472621"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref12","first-page":"30392","article-title":"Early convolutions help transformers see better","volume":"34","author":"Xiao","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"Yang","year":"2021"},{"key":"ref14","article-title":"Lite transformer with long-short range attention","author":"Wu","year":"2020"},{"key":"ref15","first-page":"23495","article-title":"Inception transformer","volume":"35","author":"Si","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref17","first-page":"9099","article-title":"Transformer quality in linear time","volume-title":"International Conference on Machine Learning","author":"Hua"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11441"},{"key":"ref19","article-title":"Mlp-based architecture with variable length input for automatic speech recognition","author":"Sakuma","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"International conference on machine learning","author":"Dauphin"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-509"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687992.pdf?arnumber=10687992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:37:57Z","timestamp":1727764677000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687992","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}