{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T07:40:09Z","timestamp":1735026009863,"version":"3.32.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Shanghai Municipal Science and Technology Commission Project","doi-asserted-by":"publisher","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800511","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"711-715","source":"Crossref","is-referenced-by-count":0,"title":["ConMamba: A Convolution-Augmented Mamba Encoder Model for Efficient End-to-End ASR Systems"],"prefix":"10.1109","author":[{"given":"Haoxiang","family":"Hou","sequence":"first","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE, Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai"}]},{"given":"Xun","family":"Gong","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE, Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE, Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref3","article-title":"Branchformer: Parallel mlp-attention architectures to capture local and global context for speech recognition and understanding","author":"Peng","year":"2022","journal-title":"ICML"},{"key":"ref4","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"International Conference on Learning Representations","author":"Gu","year":"2021"},{"key":"ref5","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume":"34","author":"Gu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref6","first-page":"35971","article-title":"On the parameterization and initialization of diagonal state space models","volume":"35","author":"Gu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","first-page":"22982","article-title":"Diagonal state spaces are as effective as structured state spaces","volume":"35","author":"Gupta","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Vivim: a video vision mamba for medical video object segmentation","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Jamba: A hybrid transformer-mamba language model","author":"Lieber","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Dual-path mamba: Short and long-term bidirectional selective structured state space models for speech separation","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Spmamba: State-space model is all you need in speech separation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3418714"},{"key":"ref15","article-title":"Con-nectionist temporal classification: labelling unsegmented se-auence data with recurrent neural networks","author":"Graves","year":"2006","journal-title":"ICML"},{"key":"ref16","article-title":"Sequence transduction with recurrent neural networks","author":"Graves","year":"2012","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2016.7472621"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref22","article-title":"Lib-rispeech: an asr corpus based on public domain audio books","author":"Panayotov","year":"2015","journal-title":"ICASSP"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800511.pdf?arnumber=10800511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:33:47Z","timestamp":1735022027000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800511","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}