{"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/reshape-dimensions-network-for-speaker-1","title":"Reshape Dimensions Network for Speaker Recognition","arxiv_id":"2407.18223","date":"2024-07-25","proceeding":null,"authors":["Ivan Yakovlev","Rostislav Makarov","Andrei Balykin","Pavel Malov","Anton Okhotnikov","Nikita Torgashov"],"abstract":"In this paper, we present Reshape Dimensions Network (ReDimNet), a novel neural network architecture for extracting utterance-level speaker representations. Our approach leverages dimensionality reshaping of 2D feature maps to 1D signal representation and vice versa, enabling the joint usage of 1D and 2D blocks. We propose an original network topology that preserves the volume of channel-timestep-frequency outputs of 1D and 2D blocks, facilitating efficient residual feature maps aggregation. Moreover, ReDimNet is efficiently scalable, and we introduce a range of model sizes, varying from 1 to 15 M parameters and from 0.5 to 20 GMACs. Our experimental results demonstrate that ReDimNet achieves state-of-the-art performance in speaker recognition while reducing computational complexity and the number of model parameters.","url_abs":"https://arxiv.org/abs/2407.18223v2","url_pdf":"https://arxiv.org/pdf/2407.18223v2.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":"reshape-dimensions-network-for-speaker-1","repo_url":"https://github.com/IDRnD/ReDimNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"speaker-recognition","task_name":"Speaker Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speaker-verification-on-voxceleb","task":"Speaker Verification","dataset":"VoxCeleb","model":"ReDimNet-B6-SF2-LM-ASNorm (15.0M)","rank_in_archive_order":2,"of":21,"metrics":{"EER":"0.37"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb","task":"Speaker Verification","dataset":"VoxCeleb","model":"ReDimNet-B5-SF2-LM-ASNorm (9.2M)","rank_in_archive_order":4,"of":21,"metrics":{"EER":"0.39"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb","task":"Speaker Verification","dataset":"VoxCeleb","model":"ReDimNet-B6-SF2-LM (15.0M)","rank_in_archive_order":5,"of":21,"metrics":{"EER":"0.4"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb","task":"Speaker Verification","dataset":"VoxCeleb","model":"ReDimNet-B5-SF2-LM (9.2M)","rank_in_archive_order":6,"of":21,"metrics":{"EER":"0.43"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb","task":"Speaker Verification","dataset":"VoxCeleb","model":"ReDimNet-B4-LM-ASNorm (6.3M)","rank_in_archive_order":7,"of":21,"metrics":{"EER":"0.44"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb","task":"Speaker Verification","dataset":"VoxCeleb","model":"ReDimNet-B3-LM-ASNorm (3.0M)","rank_in_archive_order":8,"of":21,"metrics":{"EER":"0.47"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb","task":"Speaker Verification","dataset":"VoxCeleb","model":"ReDimNet-B3-LM (3.0M)","rank_in_archive_order":9,"of":21,"metrics":{"EER":"0.5"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb","task":"Speaker Verification","dataset":"VoxCeleb","model":"ReDimNet-B4-LM (6.3M)","rank_in_archive_order":10,"of":21,"metrics":{"EER":"0.51"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb","task":"Speaker Verification","dataset":"VoxCeleb","model":"ReDimNet-B2-SF2-LM-ASNorm (4.7M)","rank_in_archive_order":11,"of":21,"metrics":{"EER":"0.52"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb","task":"Speaker Verification","dataset":"VoxCeleb","model":"ReDimNet-B2-SF2-LM (4.7M)","rank_in_archive_order":12,"of":21,"metrics":{"EER":"0.57"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb","task":"Speaker Verification","dataset":"VoxCeleb","model":"ReDimNet-B1-LM-ASNorm (2.2M)","rank_in_archive_order":14,"of":21,"metrics":{"EER":"0.73"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb","task":"Speaker Verification","dataset":"VoxCeleb","model":"ReDimNet-B1-LM (2.2M)","rank_in_archive_order":16,"of":21,"metrics":{"EER":"0.85"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb","task":"Speaker Verification","dataset":"VoxCeleb","model":"ReDimNet-B0-LM-ASNorm (1.0M)","rank_in_archive_order":18,"of":21,"metrics":{"EER":"1.07"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb","task":"Speaker Verification","dataset":"VoxCeleb","model":"ReDimNet-B0-LM (1.0M)","rank_in_archive_order":20,"of":21,"metrics":{"EER":"1.16"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb1","task":"Speaker Verification","dataset":"VoxCeleb1","model":"ReDimNet-B6-SF2-LM-ASNorm (15.0M)","rank_in_archive_order":1,"of":16,"metrics":{"EER":"0.37"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb1","task":"Speaker Verification","dataset":"VoxCeleb1","model":"ReDimNet-B5-SF2-LM-ASNorm (9.2M)","rank_in_archive_order":2,"of":16,"metrics":{"EER":"0.39"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb1","task":"Speaker Verification","dataset":"VoxCeleb1","model":"ReDimNet-B6-SF2-LM (15.0M)","rank_in_archive_order":3,"of":16,"metrics":{"EER":"0.4"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb1","task":"Speaker Verification","dataset":"VoxCeleb1","model":"ReDimNet-B5-SF2-LM (9.2M)","rank_in_archive_order":4,"of":16,"metrics":{"EER":"0.43"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb1","task":"Speaker Verification","dataset":"VoxCeleb1","model":"ReDimNet-B4-LM-ASNorm (6.3M)","rank_in_archive_order":5,"of":16,"metrics":{"EER":"0.44"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb1","task":"Speaker Verification","dataset":"VoxCeleb1","model":"ReDimNet-B3-LM-ASNorm (3.0M)","rank_in_archive_order":6,"of":16,"metrics":{"EER":"0.47"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb1","task":"Speaker Verification","dataset":"VoxCeleb1","model":"ReDimNet-B3-LM (3.0M)","rank_in_archive_order":7,"of":16,"metrics":{"EER":"0.5"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb1","task":"Speaker Verification","dataset":"VoxCeleb1","model":"ReDimNet-B4-LM (6.3M)","rank_in_archive_order":8,"of":16,"metrics":{"EER":"0.51"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb1","task":"Speaker Verification","dataset":"VoxCeleb1","model":"ReDimNet-B2-SF2-LM-ASNorm (4.7M)","rank_in_archive_order":9,"of":16,"metrics":{"EER":"0.52"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb1","task":"Speaker Verification","dataset":"VoxCeleb1","model":"ReDimNet-B2-SF2-LM (4.7M)","rank_in_archive_order":10,"of":16,"metrics":{"EER":"0.57"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb1","task":"Speaker Verification","dataset":"VoxCeleb1","model":"ReDimNet-B1-LM-ASNorm (2.2M)","rank_in_archive_order":11,"of":16,"metrics":{"EER":"0.73"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb1","task":"Speaker Verification","dataset":"VoxCeleb1","model":"ReDimNet-B1-LM (2.2M)","rank_in_archive_order":12,"of":16,"metrics":{"EER":"0.85"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb1","task":"Speaker Verification","dataset":"VoxCeleb1","model":"ReDimNet-B0-LM-ASNorm (1.0M)","rank_in_archive_order":14,"of":16,"metrics":{"EER":"1.07"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-verification-on-voxceleb1","task":"Speaker Verification","dataset":"VoxCeleb1","model":"ReDimNet-B0-LM (1.0M)","rank_in_archive_order":15,"of":16,"metrics":{"EER":"1.16"},"uses_additional_data":true}],"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":"IDRnD/ReDimNet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2602.02286"],"harvested_for_calls":[{"arxiv_id":"2602.02286","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2602.02286"},"call":"get_harvested_code_for_paper(arxiv_id=\"2602.02286\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"b2dafcadcaac4884c710f8ed2b078e67dc8396eab2c5f86a637df7f733b8a41b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}