{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/deformable-temporal-convolutional-networks","title":"Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation","arxiv_id":"2210.15305","date":"2022-10-27","proceeding":null,"authors":["William Ravenscroft","Stefan Goetze","Thomas Hain"],"abstract":"Speech separation models are used for isolating individual speakers in many speech processing applications. Deep learning models have been shown to lead to state-of-the-art (SOTA) results on a number of speech separation benchmarks. One such class of models known as temporal convolutional networks (TCNs) has shown promising results for speech separation tasks. A limitation of these models is that they have a fixed receptive field (RF). Recent research in speech dereverberation has shown that the optimal RF of a TCN varies with the reverberation characteristics of the speech signal. In this work deformable convolution is proposed as a solution to allow TCN models to have dynamic RFs that can adapt to various reverberation times for reverberant speech separation. The proposed models are capable of achieving an 11.1 dB average scale-invariant signalto-distortion ratio (SISDR) improvement over the input signal on the WHAMR benchmark. A relatively small deformable TCN model of 1.3M parameters is proposed which gives comparable separation performance to larger and more computationally complex models.","url_abs":"https://arxiv.org/abs/2210.15305v3","url_pdf":"https://arxiv.org/pdf/2210.15305v3.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":"deformable-temporal-convolutional-networks","repo_url":"https://github.com/jwr1995/dtcn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deformable-temporal-convolutional-networks","repo_url":"https://github.com/jwr1995/pubsep","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"speech-dereverberation","task_name":"Speech Dereverberation"},{"task_slug":"speech-separation","task_name":"Speech Separation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"deformable-convolution","method_name":"Deformable Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-separation-on-whamr","task":"Speech Separation","dataset":"WHAMR!","model":"Deformable TCN + Dynamic Mixing","rank_in_archive_order":15,"of":18,"metrics":{"MACs (G)":"3.7","Number of parameters (M)":"3.6","SDRi":"10.3","SI-SDRi":"11.1"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-whamr","task":"Speech Separation","dataset":"WHAMR!","model":"Deformable TCN + Shared Weights + Dynamic Mixing","rank_in_archive_order":17,"of":18,"metrics":{"MACs (G)":"3.7","Number of parameters (M)":"1.3","SDRi":"9.5","SI-SDRi":"10.1"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-2mix","task":"Speech Separation","dataset":"WSJ0-2mix","model":"Deformable TCN + Dynamic Mixing","rank_in_archive_order":32,"of":40,"metrics":{"MACs (G)":"3.7","Number of parameters (M)":"3.6","SDRi":"17.4","SI-SDRi":"17.2"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-2mix","task":"Speech Separation","dataset":"WSJ0-2mix","model":"Deformable TCN + Shared Weights + Dynamic Mixing","rank_in_archive_order":34,"of":40,"metrics":{"MACs (G)":"3.7","Number of parameters (M)":"1.3","SDRi":"16.3","SI-SDRi":"16.1"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"jwr1995/dtcn","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jwr1995/pubsep","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"104186cd3cf8e6a98d78c2014ddb50af7e1d7560f590f7e2560b44a650a07774","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}