{"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/mossformer-pushing-the-performance-limit-of","title":"MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions","arxiv_id":"2302.11824","date":"2023-02-23","proceeding":null,"authors":["Shengkui Zhao","Bin Ma"],"abstract":"Transformer based models have provided significant performance improvements in monaural speech separation. However, there is still a performance gap compared to a recent proposed upper bound. The major limitation of the current dual-path Transformer models is the inefficient modelling of long-range elemental interactions and local feature patterns. In this work, we achieve the upper bound by proposing a gated single-head transformer architecture with convolution-augmented joint self-attentions, named \\textit{MossFormer} (\\textit{Mo}naural \\textit{s}peech \\textit{s}eparation Trans\\textit{Former}). To effectively solve the indirect elemental interactions across chunks in the dual-path architecture, MossFormer employs a joint local and global self-attention architecture that simultaneously performs a full-computation self-attention on local chunks and a linearised low-cost self-attention over the full sequence. The joint attention enables MossFormer model full-sequence elemental interaction directly. In addition, we employ a powerful attentive gating mechanism with simplified single-head self-attentions. Besides the attentive long-range modelling, we also augment MossFormer with convolutions for the position-wise local pattern modelling. As a consequence, MossFormer significantly outperforms the previous models and achieves the state-of-the-art results on WSJ0-2/3mix and WHAM!/WHAMR! benchmarks. Our model achieves the SI-SDRi upper bound of 21.2 dB on WSJ0-3mix and only 0.3 dB below the upper bound of 23.1 dB on WSJ0-2mix.","url_abs":"https://arxiv.org/abs/2302.11824v1","url_pdf":"https://arxiv.org/pdf/2302.11824v1.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":"abstracts"},"code_links":[{"paper_slug":"mossformer-pushing-the-performance-limit-of","repo_url":"https://github.com/modelscope/ClearerVoice-Studio","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mossformer-pushing-the-performance-limit-of","repo_url":"https://github.com/alibabasglab/mossformer","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"speech-separation","task_name":"Speech Separation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-separation-on-wham","task":"Speech Separation","dataset":"WHAM!","model":"MossFormer (L) + DM","rank_in_archive_order":3,"of":6,"metrics":{"SI-SDRi":"17.3"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-whamr","task":"Speech Separation","dataset":"WHAMR!","model":"MossFormer (L) + DM","rank_in_archive_order":5,"of":18,"metrics":{"SI-SDRi":"16.3"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-2mix","task":"Speech Separation","dataset":"WSJ0-2mix","model":"MossFormer (L) + DM","rank_in_archive_order":10,"of":40,"metrics":{"MACs (G)":"86.1","Number of parameters (M)":"42.1","SI-SDRi":"22.8"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-2mix","task":"Speech Separation","dataset":"WSJ0-2mix","model":"MossFormer (M) + DM","rank_in_archive_order":13,"of":40,"metrics":{"SI-SDRi":"22.5"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-2mix-16k","task":"Speech Separation","dataset":"WSJ0-2mix-16k","model":"MossFormer2","rank_in_archive_order":1,"of":1,"metrics":{"SI-SDRi":"20.5"},"uses_additional_data":true},{"leaderboard":"/sota/speech-separation-on-wsj0-3mix","task":"Speech Separation","dataset":"WSJ0-3mix","model":"MossFormer (L) + DM","rank_in_archive_order":3,"of":9,"metrics":{"SI-SDRi":"21.2"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-3mix","task":"Speech Separation","dataset":"WSJ0-3mix","model":"MossFormer (M) + DM","rank_in_archive_order":5,"of":9,"metrics":{"SI-SDRi":"20.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.11824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11824"}},"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/alibabasglab/mossformer","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/modelscope/ClearerVoice-Studio","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{},"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":1,"samples":[{"code_sha256_prefix":"7f09be5e5c3deb5d","entry":"select_norm","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"7f09be5e5c3deb5d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}