{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multichannel-long-term-streaming-neural","title":"Multichannel Long-Term Streaming Neural Speech Enhancement for Static and Moving Speakers","arxiv_id":"2403.07675","date":"2024-03-12","proceeding":null,"authors":["Changsheng Quan","Xiaofei Li"],"abstract":"In this work, we extend our previously proposed offline SpatialNet for long-term streaming multichannel speech enhancement in both static and moving speaker scenarios. SpatialNet exploits spatial information, such as the spatial/steering direction of speech, for discriminating between target speech and interferences, and achieved outstanding performance. The core of SpatialNet is a narrow-band self-attention module used for learning the temporal dynamic of spatial vectors. Towards long-term streaming speech enhancement, we propose to replace the offline self-attention network with online networks that have linear inference complexity w.r.t signal length and meanwhile maintain the capability of learning long-term information. Three variants are developed based on (i) masked self-attention, (ii) Retention, a self-attention variant with linear inference complexity, and (iii) Mamba, a structured-state-space-based RNN-like network. Moreover, we investigate the length extrapolation ability of different networks, namely test on signals that are much longer than training signals, and propose a short-signal training plus long-signal fine-tuning strategy, which largely improves the length extrapolation ability of the networks within limited training time. Overall, the proposed online SpatialNet achieves outstanding speech enhancement performance for long audio streams, and for both static and moving speakers. The proposed method is open-sourced in https://github.com/Audio-WestlakeU/NBSS.","url_abs":"https://arxiv.org/abs/2403.07675v2","url_pdf":"https://arxiv.org/pdf/2403.07675v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"multichannel-long-term-streaming-neural","repo_url":"https://github.com/audio-westlakeu/nbss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.07675","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07675"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/audio-westlakeu/nbss","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":9,"unverified":1},"by_repo_kind":{"official":{"samples":10,"ran":9,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"58450c67e0f277f5","entry":"MVDR","repo":"audio-westlakeu/nbss","repo_kind":"official","path":"models/oracle_beamformer.py","file_url":"https://github.com/audio-westlakeu/nbss/blob/HEAD/models/oracle_beamformer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58450c67e0f277f5"}},{"code_sha256_prefix":"99adb47f1e62a79c","entry":"default_collate_func","repo":"audio-westlakeu/nbss","repo_kind":"official","path":"data_loaders/sms_wsj.py","file_url":"https://github.com/audio-westlakeu/nbss/blob/HEAD/data_loaders/sms_wsj.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"99adb47f1e62a79c"}},{"code_sha256_prefix":"4a970fa622717fd1","entry":"gen_obs","repo":"audio-westlakeu/nbss","repo_kind":"official","path":"data_loaders/reverb.py","file_url":"https://github.com/audio-westlakeu/nbss/blob/HEAD/data_loaders/reverb.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4a970fa622717fd1"}},{"code_sha256_prefix":"ad21d8e6a7cea754","entry":"get_shift_samples","repo":"audio-westlakeu/nbss","repo_kind":"official","path":"data_loaders/sms_wsj.py","file_url":"https://github.com/audio-westlakeu/nbss/blob/HEAD/data_loaders/sms_wsj.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ad21d8e6a7cea754"}},{"code_sha256_prefix":"1f8fdc296c7454ba","entry":"neg_si_sdr","repo":"audio-westlakeu/nbss","repo_kind":"official","path":"models/arch/NBSS.py","file_url":"https://github.com/audio-westlakeu/nbss/blob/HEAD/models/arch/NBSS.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1f8fdc296c7454ba"}},{"code_sha256_prefix":"9ed1176b4d8ac52a","entry":"randfloat","repo":"audio-westlakeu/nbss","repo_kind":"official","path":"data_loaders/spk4_wsj0_mix_sp.py","file_url":"https://github.com/audio-westlakeu/nbss/blob/HEAD/data_loaders/spk4_wsj0_mix_sp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9ed1176b4d8ac52a"}},{"code_sha256_prefix":"321d0163fb51d2fe","entry":"randint","repo":"audio-westlakeu/nbss","repo_kind":"official","path":"data_loaders/spk4_wsj0_mix_sp.py","file_url":"https://github.com/audio-westlakeu/nbss/blob/HEAD/data_loaders/spk4_wsj0_mix_sp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"321d0163fb51d2fe"}},{"code_sha256_prefix":"fca195af665563ab","entry":"reverberation_time_shortening_window","repo":"audio-westlakeu/nbss","repo_kind":"official","path":"data_loaders/sms_wsj.py","file_url":"https://github.com/audio-westlakeu/nbss/blob/HEAD/data_loaders/sms_wsj.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fca195af665563ab"}},{"code_sha256_prefix":"fd9146f3aa7abf0a","entry":"stft","repo":"audio-westlakeu/nbss","repo_kind":"official","path":"models/oracle_beamformer.py","file_url":"https://github.com/audio-westlakeu/nbss/blob/HEAD/models/oracle_beamformer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd9146f3aa7abf0a"}},{"code_sha256_prefix":"cd36ae67cf96481f","entry":"istft","repo":"audio-westlakeu/nbss","repo_kind":"official","path":"models/oracle_beamformer.py","file_url":"https://github.com/audio-westlakeu/nbss/blob/HEAD/models/oracle_beamformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cd36ae67cf96481f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}