{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:09:23Z","timestamp":1761894563126,"version":"build-2065373602"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209217","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["SPMamba: Leveraging Long-Sequence Modeling with State Space Models for Speech Separation"],"prefix":"10.1109","author":[{"given":"Kai","family":"Li","sequence":"first","affiliation":[{"name":"BNRist, THBI, IDG\/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guo","family":"Chen","sequence":"additional","affiliation":[{"name":"BNRist, THBI, IDG\/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runxuan","family":"Yang","sequence":"additional","affiliation":[{"name":"BNRist, THBI, IDG\/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolin","family":"Hu","sequence":"additional","affiliation":[{"name":"BNRist, THBI, IDG\/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231900"},{"article-title":"An efficient encoder-decoder architecture with top-down attention for speech separation","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)","author":"Li","key":"ref3"},{"key":"ref4","first-page":"22509","article-title":"Speech separation using an asynchronous fully recurrent convolutional neural network","volume":"34","author":"Hu","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-174"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096724"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747554"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094992"},{"article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"International Conference on Learning Representations","author":"Gu","key":"ref11"},{"key":"ref12","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","author":"Gu","year":"2021","journal-title":"Advances in neural information processing systems"},{"article-title":"Moe-mamba: Efficient selective state space models with mixture of experts","year":"2024","author":"Pi\u00f3ro","key":"ref13"},{"article-title":"Vmamba: Visual state space model","year":"2024","author":"Liu","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053327"},{"article-title":"Librimix: An open-source dataset for generalizable speech separation","year":"2020","author":"Cosentino","key":"ref18"},{"article-title":"Sonicsim: A customizable simulation platform for speech processing in moving sound source scenarios","year":"2024","author":"Li","key":"ref19"},{"article-title":"Linformer: Self-attention with linear complexity","year":"2020","author":"Wang","key":"ref20"},{"article-title":"Mamba: Linear-time sequence modeling with selective state spaces","year":"2023","author":"Gu","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3566210"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-994"},{"key":"ref24","first-page":"9204","article-title":"Pay attention to mlps","author":"Liu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271145"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746005"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5594\/J11396"},{"key":"ref30","article-title":"Root mean square layer normalization","volume":"32","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"article-title":"ptflops: a flops counting tool for neural networks in pytorch framework","year":"2023","author":"Sovrasov","key":"ref35"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209217.pdf?arnumber=11209217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:30:42Z","timestamp":1761888642000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209217\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209217","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}