{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:15:45Z","timestamp":1783102545386,"version":"3.54.6"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271341"],"award-info":[{"award-number":["62271341"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003398","name":"Shanxi Scholarship Council of China","doi-asserted-by":"publisher","award":["2020-127"],"award-info":[{"award-number":["2020-127"]}],"id":[{"id":"10.13039\/501100003398","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003398","name":"Shanxi Scholarship Council of China","doi-asserted-by":"publisher","award":["HGKY2019080"],"award-info":[{"award-number":["HGKY2019080"]}],"id":[{"id":"10.13039\/501100003398","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.ins.2026.123695","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T05:42:44Z","timestamp":1780292564000},"page":"123695","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Feature disentanglement in speech separation with channel-temporal fusion attention and dual-domain prototypes"],"prefix":"10.1016","volume":"754","author":[{"given":"Meng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yina","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Shangguan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2026.123695_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.specom.2025.103321","article-title":"Dynamic graph learning with gated convolutions for single-channel speech separation","author":"Zhang","year":"2025","journal-title":"Speech Commun."},{"key":"10.1016\/j.ins.2026.123695_bib0010","first-page":"1","article-title":"A review on speech separation in cocktail party environment: challenges and approaches","author":"Agrawal","year":"2023","journal-title":"Multimed. Tools Appl."},{"issue":"2","key":"10.1016\/j.ins.2026.123695_bib0015","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","article-title":"A tutorial on hidden Markov models and selected applications in speech recognition","volume":"77","author":"Rabiner","year":"1989","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.ins.2026.123695_bib0020","series-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"4280","article-title":"Multi-target doa estimation with an audio-visual fusion mechanism","author":"Qian","year":"2021"},{"key":"10.1016\/j.ins.2026.123695_bib0025","series-title":"Proceedings of the 29th ACM International Conference on Multimedia","first-page":"3927","article-title":"Is someone speaking? Exploring long-term temporal features for audio-visual active speaker detection","author":"Tao","year":"2021"},{"key":"10.1016\/j.ins.2026.123695_bib0030","series-title":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"696","article-title":"Tasnet: time-domain audio separation network for real-time, single-channel speech separation","author":"Luo","year":"2018"},{"key":"10.1016\/j.ins.2026.123695_bib0035","series-title":"Interspeech 2019","first-page":"1368","article-title":"WHAM!: Extending speech separation to noisy environments","author":"Wichern","year":"2019"},{"key":"10.1016\/j.ins.2026.123695_bib0040","author":"Cosentino"},{"key":"10.1016\/j.ins.2026.123695_bib0045","series-title":"ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"626","article-title":"SDR\u2013half-baked or well done?","author":"Roux","year":"2019"},{"issue":"4","key":"10.1016\/j.ins.2026.123695_bib0050","doi-asserted-by":"crossref","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","article-title":"Performance measurement in blind audio source separation","volume":"14","author":"Vincent","year":"2006","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"10","key":"10.1016\/j.ins.2026.123695_bib0055","doi-asserted-by":"crossref","first-page":"18995","DOI":"10.1109\/TNNLS.2025.3583747","article-title":"Robust spatiotemporal prototype learning for spiking neural networks","volume":"36","author":"Cai","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"10","key":"10.1016\/j.ins.2026.123695_bib0060","doi-asserted-by":"crossref","first-page":"14315","DOI":"10.1109\/TNNLS.2023.3278265","article-title":"A spatial\u2013channel\u2013temporal-fused attention for spiking neural networks","volume":"35","author":"Cai","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.ins.2026.123695_bib0065","doi-asserted-by":"crossref","first-page":"11912","DOI":"10.52202\/075280-0521","article-title":"What can a single attention layer learn? A study through the random features lens","volume":"36","author":"Fu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"4\u20135","key":"10.1016\/j.ins.2026.123695_bib0070","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1016\/S0893-6080(00)00026-5","article-title":"Independent component analysis: algorithms and applications","volume":"13","author":"Hyv\u00e4rinen","year":"2000","journal-title":"Neural Netw."},{"issue":"7","key":"10.1016\/j.ins.2026.123695_bib0075","doi-asserted-by":"crossref","first-page":"1483","DOI":"10.1162\/neco.1997.9.7.1483","article-title":"A fast fixed-point algorithm for independent component analysis","volume":"9","author":"Hyv\u00e4rinen","year":"1997","journal-title":"Neural Comput."},{"issue":"2","key":"10.1016\/j.ins.2026.123695_bib0080","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1162\/089976699300016719","article-title":"Independent component analysis using an extended infomax algorithm for mixed subgaussian and supergaussian sources","volume":"11","author":"Lee","year":"1999","journal-title":"Neural Comput."},{"key":"10.1016\/j.ins.2026.123695_bib0085","series-title":"IEE Proceedings F (Radar and Signal Processing)","first-page":"362","article-title":"Blind beamforming for non-Gaussian signals","volume":"vol. 140","author":"Cardoso","year":"1993"},{"key":"10.1016\/j.ins.2026.123695_bib0090","series-title":"Supervised Speech Separation Using Deep Neural Networks","author":"Wang","year":"2015"},{"key":"10.1016\/j.ins.2026.123695_bib0095","series-title":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"708","article-title":"Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks","author":"Erdogan","year":"2015"},{"issue":"10","key":"10.1016\/j.ins.2026.123695_bib0100","doi-asserted-by":"crossref","first-page":"1702","DOI":"10.1109\/TASLP.2018.2842159","article-title":"Supervised speech separation based on deep learning: an overview","volume":"26","author":"Wang","year":"2018","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.ins.2026.123695_bib0105","series-title":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"TF-gridnet: making time-frequency domain models great again for monaural speaker separation","author":"Wang","year":"2023"},{"key":"10.1016\/j.ins.2026.123695_bib0110","series-title":"The Thirteenth International Conference on Learning Representations","article-title":"TIGER: time-frequency interleaved gain extraction and reconstruction for efficient speech separation","author":"Xu","year":"2025"},{"issue":"8","key":"10.1016\/j.ins.2026.123695_bib0115","doi-asserted-by":"crossref","first-page":"1256","DOI":"10.1109\/TASLP.2019.2915167","article-title":"Conv-tasnet: surpassing ideal time\u2013frequency magnitude masking for speech separation","volume":"27","author":"Luo","year":"2019","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.ins.2026.123695_bib0120","series-title":"ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"46","article-title":"Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation","author":"Luo","year":"2020"},{"key":"10.1016\/j.ins.2026.123695_bib0125","series-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"21","article-title":"Attention is all you need in speech separation","author":"Subakan","year":"2021"},{"key":"10.1016\/j.ins.2026.123695_bib0130","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1109\/LSP.2023.3243764","article-title":"Time-domain speech separation networks with graph encoding auxiliary","volume":"30","author":"Wang","year":"2023","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.ins.2026.123695_bib0135","series-title":"The Eleventh International Conference on Learning Representations","article-title":"An efficient encoder-decoder architecture with top-down attention for speech separation","author":"Li","year":"2023"},{"key":"10.1016\/j.ins.2026.123695_bib0140","series-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Unifying speech enhancement and separation with gradient modulation for end-to-end noise-robust speech separation","author":"Hu","year":"2023"},{"key":"10.1016\/j.ins.2026.123695_bib0145","doi-asserted-by":"crossref","DOI":"10.1016\/j.specom.2024.103150","article-title":"Efficient time-domain speech separation using short encoded sequence network","volume":"166","author":"Liu","year":"2025","journal-title":"Speech Commun."},{"key":"10.1016\/j.ins.2026.123695_bib0150","author":"Li"},{"key":"10.1016\/j.ins.2026.123695_bib0155","series-title":"The Thirteenth International Conference on Learning Representations","article-title":"FIRING-net: a filtered feature recycling network for speech enhancement","author":"Xu","year":"2025"},{"key":"10.1016\/j.ins.2026.123695_bib0160","series-title":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"5206","article-title":"Librispeech: an ASR corpus based on public domain audio books","author":"Panayotov","year":"2015"},{"key":"10.1016\/j.ins.2026.123695_bib0165","article-title":"Algorithms to measure audio programme loudness and true-peak audio level","volume":"vol. 3","author":"Series","year":"2011"},{"key":"10.1016\/j.ins.2026.123695_bib0170","series-title":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"31","article-title":"Deep clustering: discriminative embeddings for segmentation and separation","author":"Hershey","year":"2016"},{"issue":"12","key":"10.1016\/j.ins.2026.123695_bib0175","doi-asserted-by":"crossref","first-page":"8717","DOI":"10.1109\/TPAMI.2018.2889052","article-title":"Deep audio-visual speech recognition","volume":"44","author":"Afouras","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.ins.2026.123695_bib0180","author":"Kingma"},{"key":"10.1016\/j.ins.2026.123695_bib0185","series-title":"Yearbook of Statistics 1991\u20132000","article-title":"International telecommunication union","year":"2001"},{"key":"10.1016\/j.ins.2026.123695_bib0190","series-title":"2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP)","first-page":"1","article-title":"Sudo RM-RF: efficient networks for universal audio source separation","author":"Tzinis","year":"2020"},{"key":"10.1016\/j.ins.2026.123695_bib0195","series-title":"Interspeech 2020","first-page":"2642","article-title":"Dual-path transformer network: direct context-aware modeling for end-to-end monaural speech separation","author":"Chen","year":"2020"},{"key":"10.1016\/j.ins.2026.123695_bib0200","first-page":"22509","article-title":"Speech separation using an asynchronous fully recurrent convolutional neural network","volume":"34","author":"Hu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.ins.2026.123695_bib0205","series-title":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1381","article-title":"Noise-aware speech separation with contrastive learning","author":"Zhang","year":"2024"},{"key":"10.1016\/j.ins.2026.123695_bib0210","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2024.104891","article-title":"Noise-aware network with shared channel-attention encoder and joint constraint for noisy speech separation","volume":"157","author":"Sun","year":"2025","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.ins.2026.123695_bib0215","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1109\/TASLP.2022.3140556","article-title":"Stepwise-refining speech separation network via fine-grained encoding in high-order latent domain","volume":"30","author":"Yao","year":"2022","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526006262?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025526006262?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:23:13Z","timestamp":1783099393000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025526006262"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":43,"alternative-id":["S0020025526006262"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2026.123695","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Feature disentanglement in speech separation with channel-temporal fusion attention and dual-domain prototypes","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2026.123695","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"123695"}}