{"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/mossformer2-combining-transformer-and-rnn-1","title":"MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation","arxiv_id":"2312.11825","date":"2023-12-19","proceeding":null,"authors":["Shengkui Zhao","Yukun Ma","Chongjia Ni","Chong Zhang","Hao Wang","Trung Hieu Nguyen","Kun Zhou","Jiaqi Yip","Dianwen Ng","Bin Ma"],"abstract":"Our previously proposed MossFormer has achieved promising performance in monaural speech separation. However, it predominantly adopts a self-attention-based MossFormer module, which tends to emphasize longer-range, coarser-scale dependencies, with a deficiency in effectively modelling finer-scale recurrent patterns. In this paper, we introduce a novel hybrid model that provides the capabilities to model both long-range, coarse-scale dependencies and fine-scale recurrent patterns by integrating a recurrent module into the MossFormer framework. Instead of applying the recurrent neural networks (RNNs) that use traditional recurrent connections, we present a recurrent module based on a feedforward sequential memory network (FSMN), which is considered \"RNN-free\" recurrent network due to the ability to capture recurrent patterns without using recurrent connections. Our recurrent module mainly comprises an enhanced dilated FSMN block by using gated convolutional units (GCU) and dense connections. In addition, a bottleneck layer and an output layer are also added for controlling information flow. The recurrent module relies on linear projections and convolutions for seamless, parallel processing of the entire sequence. The integrated MossFormer2 hybrid model demonstrates remarkable enhancements over MossFormer and surpasses other state-of-the-art methods in WSJ0-2/3mix, Libri2Mix, and WHAM!/WHAMR! benchmarks (https://github.com/modelscope/ClearerVoice-Studio).","url_abs":"https://arxiv.org/abs/2312.11825v2","url_pdf":"https://arxiv.org/pdf/2312.11825v2.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":"mossformer2-combining-transformer-and-rnn-1","repo_url":"https://github.com/modelscope/ClearerVoice-Studio","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"mossformer2-combining-transformer-and-rnn-1","repo_url":"https://github.com/alibabasglab/MossFormer2","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-separation-on-libri2mix","task":"Speech Separation","dataset":"Libri2Mix","model":"MossFormer2 (w speed perturb)","rank_in_archive_order":1,"of":10,"metrics":{"SI-SDRi":"22.2"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-libri2mix","task":"Speech Separation","dataset":"Libri2Mix","model":"MossFormer2 (w/o DM)","rank_in_archive_order":3,"of":10,"metrics":{"SI-SDRi":"21.7"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wham","task":"Speech Separation","dataset":"WHAM!","model":"MossFormer2","rank_in_archive_order":2,"of":6,"metrics":{"SI-SDRi":"18.1"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-whamr","task":"Speech Separation","dataset":"WHAMR!","model":"MossFormer2","rank_in_archive_order":4,"of":18,"metrics":{"SI-SDRi":"17.0"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-2mix","task":"Speech Separation","dataset":"WSJ0-2mix","model":"MossFormer2 (L)","rank_in_archive_order":5,"of":40,"metrics":{"Number of parameters (M)":"55.7","SI-SDRi":"24.1"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-3mix","task":"Speech Separation","dataset":"WSJ0-3mix","model":"MossFormer2","rank_in_archive_order":2,"of":9,"metrics":{"SI-SDRi":"22.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.11825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11825"}},"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/MossFormer2","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/modelscope/ClearerVoice-Studio","reach":null}],"summary":{"ran_honours":1,"ran_violates":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"named_in_paper":{"samples":3,"ran":3,"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":"5f4fdf97a20b1819","entry":"padding_to_multiple_of","repo":"alibabasglab/MossFormer2","repo_kind":"named_in_paper","path":"MossFormer2_standalone/model/utils/Transformer.py","file_url":"https://github.com/alibabasglab/MossFormer2/blob/HEAD/MossFormer2_standalone/model/utils/Transformer.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f4fdf97a20b1819"}},{"code_sha256_prefix":"60fff7c3c400d7ff","entry":"default","repo":"alibabasglab/MossFormer2","repo_kind":"named_in_paper","path":"MossFormer2_standalone/model/utils/Transformer.py","file_url":"https://github.com/alibabasglab/MossFormer2/blob/HEAD/MossFormer2_standalone/model/utils/Transformer.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"60fff7c3c400d7ff"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"alibabasglab/MossFormer2","repo_kind":"named_in_paper","path":"MossFormer2_standalone/model/utils/Transformer.py","file_url":"https://github.com/alibabasglab/MossFormer2/blob/HEAD/MossFormer2_standalone/model/utils/Transformer.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"7f09be5e5c3deb5d","entry":"select_norm","repo":"modelscope/ClearerVoice-Studio","repo_kind":"official","path":"clearvoice/clearvoice/models/mossformer2_se/mossformer2.py","file_url":"https://github.com/modelscope/ClearerVoice-Studio/blob/HEAD/clearvoice/clearvoice/models/mossformer2_se/mossformer2.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7f09be5e5c3deb5d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}