{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:58:13Z","timestamp":1776880693343,"version":"3.51.2"},"reference-count":54,"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\/icassp49660.2025.10889802","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Advancing Streaming ASR with Chunk-wise Attention and Trans-chunk Selective State Spaces"],"prefix":"10.1109","author":[{"given":"Masato","family":"Mimura","sequence":"first","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takafumi","family":"Moriya","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kohei","family":"Matsuura","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1211.3711"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1938"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref9","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"NIPS","volume":"33","author":"Baevski"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"Proceedings of ICML","author":"Chiu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688218"},{"key":"ref14","first-page":"5504","article-title":"Mu2SLAM: Multitask, Multilingual Speech and Language Models","volume-title":"ICML","author":"Cheng"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413803"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref18","article-title":"Dual-mode ASR: Unify and improve streaming ASR with full-context modeling","volume-title":"ICLR","author":"Yu"},{"key":"ref19","first-page":"32654","article-title":"Lookahead When It Matters: Adaptive Non-causal Transformers for Streaming Neural Transducers","volume-title":"ICML","author":"Strimel"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413535"},{"key":"ref22","first-page":"6783","article-title":"Emformer: Efficient memory transformer based acoustic model for low latency streaming speech recognition","volume-title":"ICASSP","author":"Yangyang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472780"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888110"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445950"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096378"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413423"},{"key":"ref28","article-title":"Hungry hungry hippos: Towards language modeling with state space models","volume-title":"ICLR","author":"Fu"},{"key":"ref29","article-title":"Hyena hierarchy: Towards larger convolutional language models","volume-title":"ICML","author":"Poli"},{"key":"ref30","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref31","article-title":"Transformers are ssms: Generalized models and efficient algorithms through structured state space duality","volume-title":"ICML","author":"Dao"},{"key":"ref32","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"ICLR","author":"Gu"},{"key":"ref33","article-title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","author":"Gu","year":"2020","journal-title":"NeurIPS"},{"key":"ref34","article-title":"On the parameterization and initialization of diagonal state space models","author":"Gu","year":"2022","journal-title":"NeurIPS"},{"key":"ref35","first-page":"22982","article-title":"Diagonal state spaces are as effective as structured state spaces","author":"Gupta","year":"2022","journal-title":"NeurIPS"},{"key":"ref36","article-title":"What makes convolutional models great on long sequence modeling?","volume-title":"ICLR","author":"Li"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832304"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1274"},{"key":"ref39","article-title":"Caduceus: Bi-directional equivariant long-range dna sequence modeling","volume-title":"ICML","author":"Schiff"},{"key":"ref40","article-title":"Parallelizing linear recurrent neural nets over sequence length","volume-title":"ICLR","author":"Martin"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096271"},{"key":"ref42","article-title":"Attention is all you need","volume-title":"NIPS","author":"Vaswani"},{"key":"ref43","first-page":"3935","article-title":"Enhancing the TED-LIUM Corpus with Selected Data for Language Modeling and More TED Talks","volume-title":"LREC","author":"Rousseau"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref46","article-title":"Branchformer: Parallel mlp-attention architectures to capture local and global context for speech recognition and understanding","volume-title":"ICML","author":"Peng"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref48","article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR","author":"Kingma"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10340"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1036"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-994"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-258"}],"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\/10889802.pdf?arnumber=10889802","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:49Z","timestamp":1774416289000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889802\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889802","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}