{"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":"/task/speaker-recognition/papers/ran/1","list_of":"/task/speaker-recognition","task":"Speaker Recognition","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,17],"of":17,"counts":{"archive_papers_tagged":435,"with_a_code_link":102,"where_syntology_ran_a_sample":17,"not_listed_spam_title":0,"listed":435,"listed_where_code_ran":17,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":15,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":15,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/speaker-recognition/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/voxsim-a-perceptual-voice-similarity-dataset","slug":"voxsim-a-perceptual-voice-similarity-dataset","title":"VoxSim: A perceptual voice similarity dataset","date":"2024-07-26","arxiv_id":"2407.18505","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/voxsim-a-perceptual-voice-similarity-dataset#ran","syntology_url":"https://syntology.ai/paper/2407.18505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.18505"}},"official":{"repos":["kaistmm/voxsim_trainer"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/certification-of-speaker-recognition-models","slug":"certification-of-speaker-recognition-models","title":"Certification of Speaker Recognition Models to Additive Perturbations","date":"2024-04-29","arxiv_id":"2404.18791","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/certification-of-speaker-recognition-models#ran","syntology_url":"https://syntology.ai/paper/2404.18791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18791"}},"official":{"repos":["airi-institute/asi-certification"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/espnet-spk-full-pipeline-speaker-embedding","slug":"espnet-spk-full-pipeline-speaker-embedding","title":"ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models","date":"2024-01-30","arxiv_id":"2401.17230","repositories_listed":2,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/espnet-spk-full-pipeline-speaker-embedding#ran","syntology_url":"https://syntology.ai/paper/2401.17230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17230"}},"official":{"repos":["espnet/espnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/can-self-supervised-neural-networks-pre","slug":"can-self-supervised-neural-networks-pre","title":"Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers?","date":"2023-05-23","arxiv_id":"2305.14035","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/can-self-supervised-neural-networks-pre#ran","syntology_url":"https://syntology.ai/paper/2305.14035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14035"}},"official":{"repos":["idiap/ssl-caller-detection"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/olkavs-an-open-large-scale-korean-audio","slug":"olkavs-an-open-large-scale-korean-audio","title":"OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset","date":"2023-01-16","arxiv_id":"2301.06375","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/olkavs-an-open-large-scale-korean-audio#ran","syntology_url":"https://syntology.ai/paper/2301.06375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.06375"}},"official":{"repos":["iip-sogang/olkavs-avspeech"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-understanding-and-mitigating-audio","slug":"towards-understanding-and-mitigating-audio","title":"Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognition","date":"2022-06-07","arxiv_id":"2206.03393","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-understanding-and-mitigating-audio#ran","syntology_url":"https://syntology.ai/paper/2206.03393","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03393"}},"official":null}},{"url":"/paper/improving-fairness-in-speaker-verification","slug":"improving-fairness-in-speaker-verification","title":"Improving fairness in speaker verification via Group-adapted Fusion Network","date":"2022-02-23","arxiv_id":"2202.11323","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-fairness-in-speaker-verification#ran","syntology_url":"https://syntology.ai/paper/2202.11323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.11323"}},"official":{"repos":["huashen218/voxceleb-fairness"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-speaker-recognition-with-loss","slug":"self-supervised-speaker-recognition-with-loss","title":"Self-supervised Speaker Recognition with Loss-gated Learning","date":"2021-10-08","arxiv_id":"2110.03869","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-supervised-speaker-recognition-with-loss#ran","syntology_url":"https://syntology.ai/paper/2110.03869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03869"}},"official":{"repos":["taoruijie/loss-gated-learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pretext-tasks-selection-for-multitask-self","slug":"pretext-tasks-selection-for-multitask-self","title":"Pretext Tasks selection for multitask self-supervised speech representation learning","date":"2021-07-01","arxiv_id":"2107.00594","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pretext-tasks-selection-for-multitask-self#ran","syntology_url":"https://syntology.ai/paper/2107.00594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00594"}},"official":{"repos":["salah-zaiem/PL-groupselection"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tera-self-supervised-learning-of-transformer","slug":"tera-self-supervised-learning-of-transformer","title":"TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech","date":"2020-07-12","arxiv_id":"2007.06028","repositories_listed":7,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tera-self-supervised-learning-of-transformer#ran","syntology_url":"https://syntology.ai/paper/2007.06028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06028"}},"official":{"repos":["andi611/Self-Supervised-Speech-Pretraining-and-Representation-Learning","s3prl/s3prl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/mockingjay-unsupervised-speech-representation","slug":"mockingjay-unsupervised-speech-representation","title":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","date":"2019-10-25","arxiv_id":"1910.12638","repositories_listed":7,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mockingjay-unsupervised-speech-representation#ran","syntology_url":"https://syntology.ai/paper/1910.12638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12638"}},"official":{"repos":["andi611/Self-Supervised-Speech-Pretraining-and-Representation-Learning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/filterbank-design-for-end-to-end-speech","slug":"filterbank-design-for-end-to-end-speech","title":"Filterbank design for end-to-end speech separation","date":"2019-10-23","arxiv_id":"1910.10400","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/filterbank-design-for-end-to-end-speech#ran","syntology_url":"https://syntology.ai/paper/1910.10400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10400"}},"official":{"repos":["mpariente/AsSteroid"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/utterance-level-aggregation-for-speaker","slug":"utterance-level-aggregation-for-speaker","title":"Utterance-level Aggregation For Speaker Recognition In The Wild","date":"2019-02-26","arxiv_id":"1902.10107","repositories_listed":10,"syntology":{"n":23,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/utterance-level-aggregation-for-speaker#ran","syntology_url":"https://syntology.ai/paper/1902.10107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.10107"}},"official":{"repos":["WeidiXie/VGG-Speaker-Recognition"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/voicefilter-targeted-voice-separation-by","slug":"voicefilter-targeted-voice-separation-by","title":"VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking","date":"2018-10-11","arxiv_id":"1810.04826","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/voicefilter-targeted-voice-separation-by#ran","syntology_url":"https://syntology.ai/paper/1810.04826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.04826"}},"official":null}},{"url":"/paper/speaker-recognition-from-raw-waveform-with","slug":"speaker-recognition-from-raw-waveform-with","title":"Speaker Recognition from Raw Waveform with SincNet","date":"2018-07-29","arxiv_id":"1808.00158","repositories_listed":26,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/speaker-recognition-from-raw-waveform-with#ran","syntology_url":"https://syntology.ai/paper/1808.00158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.00158"}},"official":{"repos":["mravanelli/SincNet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/voxceleb2-deep-speaker-recognition","slug":"voxceleb2-deep-speaker-recognition","title":"VoxCeleb2: Deep Speaker Recognition","date":"2018-06-14","arxiv_id":"1806.05622","repositories_listed":2,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/voxceleb2-deep-speaker-recognition#ran","syntology_url":"https://syntology.ai/paper/1806.05622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.05622"}},"official":null}},{"url":"/paper/deep-speaker-an-end-to-end-neural-speaker","slug":"deep-speaker-an-end-to-end-neural-speaker","title":"Deep Speaker: an End-to-End Neural Speaker Embedding System","date":"2017-05-05","arxiv_id":"1705.02304","repositories_listed":15,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-speaker-an-end-to-end-neural-speaker#ran","syntology_url":"https://syntology.ai/paper/1705.02304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.02304"}},"official":null}}],"record_sha256":"c9ee972bc6c159f6b88fef60f0afce56903f05503fe36eae6e088f9d795fa6c0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}