{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T20:18:43Z","timestamp":1770495523022,"version":"3.49.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095430","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":18,"title":["UCONV-Conformer: High Reduction of Input Sequence Length for End-to-End Speech Recognition"],"prefix":"10.1109","author":[{"given":"Andrei","family":"Andrusenko","sequence":"first","affiliation":[{"name":"ITMO University,St. Petersburg,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rauf","family":"Nasretdinov","sequence":"additional","affiliation":[{"name":"STC-Innovations Ltd,St. Petersburg,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aleksei","family":"Romanenko","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2361"},{"key":"ref12","article-title":"Transformers are rnns: Fast autoregressive transformers with linear attention","author":"katharopoulos","year":"2020","journal-title":"Proc ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687874"},{"key":"ref11","author":"wu","year":"2021","journal-title":"Fastformer Additive attention can be all you need"},{"key":"ref10","article-title":"Branchformer: Parallel MLP-attention architectures to capture local and global context for speech recognition and understanding","author":"peng","year":"2022","journal-title":"Proc PMLR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1819"},{"key":"ref17","article-title":"Squeezeformer: An efficient transformer for automatic speech recognition","author":"kim","year":"2022","journal-title":"NeurIPS"},{"key":"ref16","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"MICCAI"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_4"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref8","author":"beltagy","year":"2020","journal-title":"Longformer The long-document transformer"},{"key":"ref7","article-title":"Efficient transformers: A survey","author":"tay","year":"2022","journal-title":"ACM Com-put Surv"},{"key":"ref9","article-title":"Big bird: Transformers for longer sequences","author":"zaheer","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref3","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Red Hook NY USA"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10723"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095430.pdf?arnumber=10095430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:08:11Z","timestamp":1700507291000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095430","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}