{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:22:16Z","timestamp":1766067736615,"version":"3.28.0"},"reference-count":32,"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\/icassp49357.2023.10096271","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":9,"title":["Diagonal State Space Augmented Transformers for Speech Recognition"],"prefix":"10.1109","author":[{"given":"George","family":"Saon","sequence":"first","affiliation":[{"name":"IBM Research AI,Yorktown Heights,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankit","family":"Gupta","sequence":"additional","affiliation":[{"name":"IBM Research AI,Yorktown Heights,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodong","family":"Cui","sequence":"additional","affiliation":[{"name":"IBM Research AI,Yorktown Heights,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687874"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref15","first-page":"arxiv","author":"wang","year":"2020","journal-title":"Efficient end-to-end speech recognition using performers in conformers"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198756"},{"key":"ref30","volume":"abs 2204 10586","author":"zhou","year":"2022","journal-title":"Efficient Training of Neural Transducer for Speech Recognition"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747706"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1907"},{"key":"ref2","article-title":"Hippo: Recurrent memory with optimal polynomial projections","author":"gu","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33 Annual Conference on Neural Information Processing Systems 2020 NeurIPS 2020"},{"key":"ref1","volume":"abs 2111 396","author":"gu","year":"2021","journal-title":"Efficiently modeling long sequences with structured state spaces"},{"key":"ref17","volume":"abs 2206 14747","author":"jiang","year":"2022","journal-title":"Nextformer A convnext augmented conformer for end-to-end speech recognition"},{"key":"ref16","first-page":"448","article-title":"Efficient conformer-based speech recognition with linear attention","author":"li","year":"2021","journal-title":"2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414716"},{"key":"ref18","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding"},{"journal-title":"Sequence transduction with recurrent neural networks","year":"2012","author":"graves","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053040"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747418"},{"key":"ref20","volume":"abs 2203 15176","author":"cui","year":"2022","journal-title":"Improving generalization of deep neural network acoustic models with length perturbation and n-best based label smoothing"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683706"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003790"},{"journal-title":"Fnet Mixing tokens with fourier transforms","year":"2021","author":"lee-thorp","key":"ref29"},{"key":"ref8","first-page":"2062","article-title":"On the limit of english conversational speech recognition","author":"t\u00fcske","year":"2021","journal-title":"22nd Annual Conference of the International Speech Communication Association INTERSPEECH 2021"},{"key":"ref7","volume":"abs 2206 12955","author":"zeineldeen","year":"2022","journal-title":"Improving the training recipe for a robust conformer-based hybrid model"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747879"},{"key":"ref4","volume":"abs 2206 13947","author":"mehta","year":"2022","journal-title":"Long range language modeling via gated state spaces"},{"key":"ref3","volume":"abs 2203 14343","author":"gupta","year":"2022","journal-title":"Diagonal state spaces are as effective as structured state spaces"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref5","volume":"abs 2206 11893","author":"gu","year":"2022","journal-title":"On the parameterization and initialization of diagonal state space models"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10096271.pdf?arnumber=10096271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:02:51Z","timestamp":1699902171000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096271\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096271","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}