{"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","name":"Speaker Recognition","slug":"speaker-recognition","description_markdown":"**Speaker Recognition** is the process of identifying or confirming the identity of a person given his speech segments.\n\n\n<span class=\"description-source\">Source: [Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition ](https://arxiv.org/abs/1906.07317)</span>","categories":[{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":435,"papers_with_code":102,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":6,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/speaker-recognition-on-voxceleb1","slug":"speaker-recognition-on-voxceleb1","dataset":"VoxCeleb1","dataset_url":"/dataset/voxceleb1","rows_in_archive":2,"metrics":["EER"],"first_row_in_archive_order":{"model":"WavLM+ECAPA-TDNN","paper_title":"ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models","paper_url":"/paper/espnet-spk-full-pipeline-speaker-embedding","paper_date":"2024-01-30","arxiv_id":"2401.17230","code_links":[{"title":"espnet/espnet","url":"https://github.com/espnet/espnet"},{"title":"Jungjee/RawNet","url":"https://github.com/Jungjee/RawNet"}],"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 3 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"]}}}}],"datasets":[{"url":"/dataset/voxceleb1","name":"VoxCeleb1","full_name":"VoxCeleb1","num_papers_in_archive":680},{"url":"/dataset/vgg-sound","name":"VGG-Sound","full_name":"","num_papers_in_archive":211},{"url":"/dataset/cn-celeb","name":"CN-CELEB","full_name":"","num_papers_in_archive":68},{"url":"/dataset/fkd","name":"FKD","full_name":"Football Keywords Dataset","num_papers_in_archive":2},{"url":"/dataset/mavs","name":"MAVS","full_name":"Multilingual Audio-Visual Smartphone dataset","num_papers_in_archive":2},{"url":"/dataset/asr-ramc-bigccsc-a-chinese-conversational","name":"ASR-RAMC-BIGCCSC: A CHINESE CONVERSATIONAL SPEECH CORPUS","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":5,"rows_per_page":100,"shown":100,"of":435,"of_with_code":102,"tagged_in_all":435,"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"},"items":[{"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/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}},{"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/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/three-dimensional-lip-motion-network-for-text","slug":"three-dimensional-lip-motion-network-for-text","title":"Three-Dimensional Lip Motion Network for Text-Independent Speaker Recognition","date":"2020-10-13","arxiv_id":"2010.06363","repositories_listed":6,"syntology":null},{"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/fine-tuning-wav2vec2-for-speaker-recognition","slug":"fine-tuning-wav2vec2-for-speaker-recognition","title":"Fine-tuning wav2vec2 for speaker recognition","date":"2021-09-30","arxiv_id":"2109.15053","repositories_listed":4,"syntology":null},{"url":"/paper/probabilistic-spherical-discriminant-analysis","slug":"probabilistic-spherical-discriminant-analysis","title":"Probabilistic Spherical Discriminant Analysis: An Alternative to PLDA for length-normalized embeddings","date":"2022-03-28","arxiv_id":"2203.14893","repositories_listed":3,"syntology":null},{"url":"/paper/hlt-nus-submission-for-2020-nist","slug":"hlt-nus-submission-for-2020-nist","title":"HLT-NUS SUBMISSION FOR 2020 NIST Conversational Telephone Speech SRE","date":"2021-11-12","arxiv_id":"2111.06671","repositories_listed":3,"syntology":null},{"url":"/paper/autospeech-neural-architecture-search-for","slug":"autospeech-neural-architecture-search-for","title":"AutoSpeech: Neural Architecture Search for Speaker Recognition","date":"2020-05-07","arxiv_id":"2005.03215","repositories_listed":3,"syntology":null},{"url":"/paper/am-mobilenet1d-a-portable-model-for-speaker","slug":"am-mobilenet1d-a-portable-model-for-speaker","title":"AM-MobileNet1D: A Portable Model for Speaker Recognition","date":"2020-03-31","arxiv_id":"2004.00132","repositories_listed":3,"syntology":null},{"url":"/paper/3d-speaker-toolkit-an-open-source-toolkit-for","slug":"3d-speaker-toolkit-an-open-source-toolkit-for","title":"3D-Speaker-Toolkit: An Open-Source Toolkit for Multimodal Speaker Verification and Diarization","date":"2024-03-29","arxiv_id":"2403.19971","repositories_listed":2,"syntology":null},{"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":6,"n_instrument":3,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 3 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/taploss-a-temporal-acoustic-parameter-loss","slug":"taploss-a-temporal-acoustic-parameter-loss","title":"TAPLoss: A Temporal Acoustic Parameter Loss for Speech Enhancement","date":"2023-02-16","arxiv_id":"2302.08088","repositories_listed":2,"syntology":null},{"url":"/paper/toroidal-probabilistic-spherical-discriminant","slug":"toroidal-probabilistic-spherical-discriminant","title":"Toroidal Probabilistic Spherical Discriminant Analysis","date":"2022-10-27","arxiv_id":"2210.15441","repositories_listed":2,"syntology":null},{"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/paddlespeech-an-easy-to-use-all-in-one-speech-1","slug":"paddlespeech-an-easy-to-use-all-in-one-speech-1","title":"PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit","date":"2022-05-20","arxiv_id":"2205.12007","repositories_listed":2,"syntology":null},{"url":"/paper/raw-waveform-speaker-verification-for","slug":"raw-waveform-speaker-verification-for","title":"Pushing the limits of raw waveform speaker recognition","date":"2022-03-16","arxiv_id":"2203.08488","repositories_listed":2,"syntology":null},{"url":"/paper/speaker-anonymisation-using-the-mcadams","slug":"speaker-anonymisation-using-the-mcadams","title":"Speaker anonymisation using the McAdams coefficient","date":"2020-11-02","arxiv_id":"2011.01130","repositories_listed":2,"syntology":null},{"url":"/paper/crossed-time-delay-neural-network-for-speaker","slug":"crossed-time-delay-neural-network-for-speaker","title":"Crossed-Time Delay Neural Network for Speaker Recognition","date":"2020-05-31","arxiv_id":"2006.00452","repositories_listed":2,"syntology":null},{"url":"/paper/speech2phone-a-multilingual-and-text","slug":"speech2phone-a-multilingual-and-text","title":"Speech2Phone: A Novel and Efficient Method for Training Speaker Recognition Models","date":"2020-02-25","arxiv_id":"2002.11213","repositories_listed":2,"syntology":null},{"url":"/paper/cn-celeb-a-challenging-chinese-speaker","slug":"cn-celeb-a-challenging-chinese-speaker","title":"CN-CELEB: a challenging Chinese speaker recognition dataset","date":"2019-10-31","arxiv_id":"1911.01799","repositories_listed":2,"syntology":null},{"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/personal-vad-speaker-conditioned-voice","slug":"personal-vad-speaker-conditioned-voice","title":"Personal VAD: Speaker-Conditioned Voice Activity Detection","date":"2019-08-12","arxiv_id":"1908.04284","repositories_listed":2,"syntology":null},{"url":"/paper/speech-and-speaker-recognition-from-raw","slug":"speech-and-speaker-recognition-from-raw","title":"Speech and Speaker Recognition from Raw Waveform with SincNet","date":"2018-12-13","arxiv_id":"1812.05920","repositories_listed":2,"syntology":null},{"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/attention-based-models-for-text-dependent","slug":"attention-based-models-for-text-dependent","title":"Attention-Based Models for Text-Dependent Speaker Verification","date":"2017-10-28","arxiv_id":"1710.10470","repositories_listed":2,"syntology":null},{"url":"/paper/colmbo-speaker-language-model-for-descriptive","slug":"colmbo-speaker-language-model-for-descriptive","title":"CoLMbo: Speaker Language Model for Descriptive Profiling","date":"2025-06-11","arxiv_id":"2506.09375","repositories_listed":1,"syntology":null},{"url":"/paper/private-knn-vc-interpretable-anonymization-of","slug":"private-knn-vc-interpretable-anonymization-of","title":"Private kNN-VC: Interpretable Anonymization of Converted Speech","date":"2025-05-23","arxiv_id":"2505.17584","repositories_listed":1,"syntology":null},{"url":"/paper/seed-speaker-embedding-enhancement-diffusion","slug":"seed-speaker-embedding-enhancement-diffusion","title":"SEED: Speaker Embedding Enhancement Diffusion Model","date":"2025-05-22","arxiv_id":"2505.16798","repositories_listed":1,"syntology":null},{"url":"/paper/usef-tse-universal-speaker-embedding-free","slug":"usef-tse-universal-speaker-embedding-free","title":"USEF-TSE: Universal Speaker Embedding Free Target Speaker Extraction","date":"2024-09-04","arxiv_id":"2409.02615","repositories_listed":1,"syntology":null},{"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":4,"n_instrument":9,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 9 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":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reshape-dimensions-network-for-speaker-1","slug":"reshape-dimensions-network-for-speaker-1","title":"Reshape Dimensions Network for Speaker Recognition","date":"2024-07-25","arxiv_id":"2407.18223","repositories_listed":1,"syntology":null},{"url":"/paper/voxblink2-a-100k-speaker-recognition-corpus","slug":"voxblink2-a-100k-speaker-recognition-corpus","title":"VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmark","date":"2024-07-16","arxiv_id":"2407.11510","repositories_listed":1,"syntology":null},{"url":"/paper/a-voice-and-speech-corpus-of-patients-who","slug":"a-voice-and-speech-corpus-of-patients-who","title":"A voice and speech corpus of patients who underwent upper airway surgery in pre- and post-operative states","date":"2024-07-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/prosody-driven-privacy-preserving-dementia","slug":"prosody-driven-privacy-preserving-dementia","title":"Prosody-Driven Privacy-Preserving Dementia Detection","date":"2024-07-03","arxiv_id":"2407.03470","repositories_listed":1,"syntology":null},{"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":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 1 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":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/take-the-atrain-introducing-an-interface-for","slug":"take-the-atrain-introducing-an-interface-for","title":"Take the aTrain. Introducing an Interface for the Accessible Transcription of Interviews","date":"2023-10-18","arxiv_id":"2310.11967","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-in-the-wild-data-for-effective","slug":"leveraging-in-the-wild-data-for-effective","title":"Leveraging In-the-Wild Data for Effective Self-Supervised Pretraining in Speaker Recognition","date":"2023-09-21","arxiv_id":"2309.11730","repositories_listed":1,"syntology":null},{"url":"/paper/slmia-sr-speaker-level-membership-inference","slug":"slmia-sr-speaker-level-membership-inference","title":"SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems","date":"2023-09-14","arxiv_id":"2309.07983","repositories_listed":1,"syntology":null},{"url":"/paper/speechglue-how-well-can-self-supervised","slug":"speechglue-how-well-can-self-supervised","title":"SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?","date":"2023-06-14","arxiv_id":"2306.08374","repositories_listed":1,"syntology":null},{"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/vocal-style-factorization-for-effective","slug":"vocal-style-factorization-for-effective","title":"Vocal Style Factorization for Effective Speaker Recognition in Affective Scenarios","date":"2023-05-13","arxiv_id":"2305.07997","repositories_listed":1,"syntology":null},{"url":"/paper/voxsrc-2022-the-fourth-voxceleb-speaker","slug":"voxsrc-2022-the-fourth-voxceleb-speaker","title":"VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challenge","date":"2023-02-20","arxiv_id":"2302.10248","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-back-ends-for-online-speaker","slug":"probabilistic-back-ends-for-online-speaker","title":"Probabilistic Back-ends for Online Speaker Recognition and Clustering","date":"2023-02-19","arxiv_id":"2302.09523","repositories_listed":1,"syntology":null},{"url":"/paper/masking-kernel-for-learning-energy-efficient","slug":"masking-kernel-for-learning-energy-efficient","title":"Masking Kernel for Learning Energy-Efficient Representations for Speaker Recognition and Mobile Health","date":"2023-02-08","arxiv_id":"2302.04161","repositories_listed":1,"syntology":null},{"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/noisy-label-detection-for-speaker-recognition","slug":"noisy-label-detection-for-speaker-recognition","title":"Inconsistency Ranking-based Noisy Label Detection for High-quality Data","date":"2022-12-01","arxiv_id":"2212.00239","repositories_listed":1,"syntology":null},{"url":"/paper/is-style-all-you-need-dependencies-between","slug":"is-style-all-you-need-dependencies-between","title":"Is Style All You Need? Dependencies Between Emotion and GST-based Speaker Recognition","date":"2022-11-15","arxiv_id":"2211.08213","repositories_listed":1,"syntology":null},{"url":"/paper/speaker-recognition-with-two-step-multi-modal","slug":"speaker-recognition-with-two-step-multi-modal","title":"Speaker recognition with two-step multi-modal deep cleansing","date":"2022-10-28","arxiv_id":"2210.15903","repositories_listed":1,"syntology":null},{"url":"/paper/risk-of-re-identification-for-shared-clinical","slug":"risk-of-re-identification-for-shared-clinical","title":"Risk of re-identification for shared clinical speech recordings","date":"2022-10-18","arxiv_id":"2210.09975","repositories_listed":1,"syntology":null},{"url":"/paper/merkel-podcast-corpus-a-multimodal-dataset-1","slug":"merkel-podcast-corpus-a-multimodal-dataset-1","title":"Merkel Podcast Corpus: A Multimodal Dataset Compiled from 16 Years of Angela Merkel’s Weekly Video Podcasts","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/merkel-podcast-corpus-a-multimodal-dataset","slug":"merkel-podcast-corpus-a-multimodal-dataset","title":"Merkel Podcast Corpus: A Multimodal Dataset Compiled from 16 Years of Angela Merkel's Weekly Video Podcasts","date":"2022-05-24","arxiv_id":"2205.12194","repositories_listed":1,"syntology":null},{"url":"/paper/speaker-recognition-in-the-wild","slug":"speaker-recognition-in-the-wild","title":"Speaker Recognition in the Wild","date":"2022-05-05","arxiv_id":"2205.02475","repositories_listed":1,"syntology":null},{"url":"/paper/baselines-and-protocols-for-household-speaker","slug":"baselines-and-protocols-for-household-speaker","title":"Baselines and Protocols for Household Speaker Recognition","date":"2022-04-30","arxiv_id":"2205.00288","repositories_listed":1,"syntology":null},{"url":"/paper/training-speaker-recognition-systems-with","slug":"training-speaker-recognition-systems-with","title":"Training speaker recognition systems with limited data","date":"2022-03-28","arxiv_id":"2203.14688","repositories_listed":1,"syntology":null},{"url":"/paper/to-train-or-not-to-train-adversarially-a","slug":"to-train-or-not-to-train-adversarially-a","title":"To train or not to train adversarially: A study of bias mitigation strategies for speaker recognition","date":"2022-03-17","arxiv_id":"2203.09122","repositories_listed":1,"syntology":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/deepsensor-deep-learning-testing-framework","slug":"deepsensor-deep-learning-testing-framework","title":"Excitement Surfeited Turns to Errors: Deep Learning Testing Framework Based on Excitable Neurons","date":"2022-02-12","arxiv_id":"2202.07464","repositories_listed":1,"syntology":null},{"url":"/paper/bias-in-automated-speaker-recognition","slug":"bias-in-automated-speaker-recognition","title":"Bias in Automated Speaker Recognition","date":"2022-01-24","arxiv_id":"2201.09486","repositories_listed":1,"syntology":null},{"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":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"3 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; 1 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":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/temporal-dynamic-convolutional-neural-network","slug":"temporal-dynamic-convolutional-neural-network","title":"Temporal Dynamic Convolutional Neural Network for Text-Independent Speaker Verification and Phonemetic Analysis","date":"2021-10-07","arxiv_id":"2110.03213","repositories_listed":1,"syntology":null},{"url":"/paper/voxceleb-enrichment-for-age-and-gender","slug":"voxceleb-enrichment-for-age-and-gender","title":"VoxCeleb Enrichment for Age and Gender Recognition","date":"2021-09-28","arxiv_id":"2109.13510","repositories_listed":1,"syntology":null},{"url":"/paper/speechnas-towards-better-trade-off-between","slug":"speechnas-towards-better-trade-off-between","title":"SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification","date":"2021-09-18","arxiv_id":"2109.08839","repositories_listed":1,"syntology":null},{"url":"/paper/sec4sr-a-security-analysis-platform-for","slug":"sec4sr-a-security-analysis-platform-for","title":"SEC4SR: A Security Analysis Platform for Speaker Recognition","date":"2021-09-04","arxiv_id":"2109.01766","repositories_listed":1,"syntology":null},{"url":"/paper/curricular-sincnet-towards-robust-deep","slug":"curricular-sincnet-towards-robust-deep","title":"Curricular SincNet: Towards Robust Deep Speaker Recognition by Emphasizing Hard Samples in Latent Space","date":"2021-08-21","arxiv_id":"2108.10714","repositories_listed":1,"syntology":null},{"url":"/paper/use-of-speaker-recognition-approaches-for","slug":"use-of-speaker-recognition-approaches-for","title":"Use of speaker recognition approaches for learning and evaluating embedding representations of musical instrument sounds","date":"2021-07-24","arxiv_id":"2107.11506","repositories_listed":1,"syntology":null},{"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/speaker-identification-from-raw-waveform-with","slug":"speaker-identification-from-raw-waveform-with","title":"PF-Net: Personalized Filter for Speaker Recognition from Raw Waveform","date":"2021-05-31","arxiv_id":"2105.14826","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-deep-learning-for-joint-audio","slug":"exploring-deep-learning-for-joint-audio","title":"Exploring Deep Learning for Joint Audio-Visual Lip Biometrics","date":"2021-04-17","arxiv_id":"2104.08510","repositories_listed":1,"syntology":null},{"url":"/paper/conditional-independence-for-pretext-task","slug":"conditional-independence-for-pretext-task","title":"Conditional independence for pretext task selection in Self-supervised speech representation learning","date":"2021-04-15","arxiv_id":"2104.07388","repositories_listed":1,"syntology":null},{"url":"/paper/speaker-embeddings-by-modeling-channel-wise","slug":"speaker-embeddings-by-modeling-channel-wise","title":"Speaker embeddings by modeling channel-wise correlations","date":"2021-04-06","arxiv_id":"2104.02571","repositories_listed":1,"syntology":null},{"url":"/paper/dr-vectors-decision-residual-networks-and-an","slug":"dr-vectors-decision-residual-networks-and-an","title":"Dr-Vectors: Decision Residual Networks and an Improved Loss for Speaker Recognition","date":"2021-04-05","arxiv_id":"2104.01989","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-to-many-languages-with-a-triaged","slug":"scaling-to-many-languages-with-a-triaged","title":"SpeakerStew: Scaling to Many Languages with a Triaged Multilingual Text-Dependent and Text-Independent Speaker Verification System","date":"2021-04-05","arxiv_id":"2104.02125","repositories_listed":1,"syntology":null},{"url":"/paper/efficienttdnn-efficient-architecture-search","slug":"efficienttdnn-efficient-architecture-search","title":"EfficientTDNN: Efficient Architecture Search for Speaker Recognition","date":"2021-03-25","arxiv_id":"2103.13581","repositories_listed":1,"syntology":null},{"url":"/paper/u-vectors-generating-clusterable-speaker","slug":"u-vectors-generating-clusterable-speaker","title":"U-vectors: Generating clusterable speaker embedding from unlabeled data","date":"2021-02-07","arxiv_id":"2102.03868","repositories_listed":1,"syntology":null},{"url":"/paper/deeptalk-vocal-style-encoding-for-speaker","slug":"deeptalk-vocal-style-encoding-for-speaker","title":"DeepTalk: Vocal Style Encoding for Speaker Recognition and Speech Synthesis","date":"2020-12-09","arxiv_id":"2012.05084","repositories_listed":1,"syntology":null},{"url":"/paper/sar-net-a-end-to-end-deep-speech-accent","slug":"sar-net-a-end-to-end-deep-speech-accent","title":"Deep Discriminative Feature Learning for Accent Recognition","date":"2020-11-25","arxiv_id":"2011.12461","repositories_listed":1,"syntology":null},{"url":"/paper/covid-19-patient-detection-from-telephone","slug":"covid-19-patient-detection-from-telephone","title":"COVID-19 Patient Detection from Telephone Quality Speech Data","date":"2020-11-09","arxiv_id":"2011.04299","repositories_listed":1,"syntology":null},{"url":"/paper/mask-proxy-loss-for-text-independent-speaker","slug":"mask-proxy-loss-for-text-independent-speaker","title":"Masked Proxy Loss For Text-Independent Speaker Verification","date":"2020-11-09","arxiv_id":"2011.04491","repositories_listed":1,"syntology":null},{"url":"/paper/deep-generative-lda","slug":"deep-generative-lda","title":"Deep generative LDA","date":"2020-10-30","arxiv_id":"2010.16138","repositories_listed":1,"syntology":null},{"url":"/paper/deep-speaker-vector-normalization-with","slug":"deep-speaker-vector-normalization-with","title":"Deep Speaker Vector Normalization with Maximum Gaussianality Training","date":"2020-10-30","arxiv_id":"2010.16148","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-speaker-attribute-information","slug":"leveraging-speaker-attribute-information","title":"Leveraging speaker attribute information using multi task learning for speaker verification and diarization","date":"2020-10-27","arxiv_id":"2010.14269","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-representation-learning-for-1","slug":"unsupervised-representation-learning-for-1","title":"Unsupervised Representation Learning for Speaker Recognition via Contrastive Equilibrium Learning","date":"2020-10-22","arxiv_id":"2010.11433","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-attack-and-defense-strategies-for","slug":"adversarial-attack-and-defense-strategies-for","title":"Adversarial Attack and Defense Strategies for Deep Speaker Recognition Systems","date":"2020-08-18","arxiv_id":"2008.07685","repositories_listed":1,"syntology":null},{"url":"/paper/neural-plda-modeling-for-end-to-end-speaker","slug":"neural-plda-modeling-for-end-to-end-speaker","title":"Neural PLDA Modeling for End-to-End Speaker Verification","date":"2020-08-11","arxiv_id":"2008.04527","repositories_listed":1,"syntology":null},{"url":"/paper/version-control-of-speaker-recognition","slug":"version-control-of-speaker-recognition","title":"Version Control of Speaker Recognition Systems","date":"2020-07-23","arxiv_id":"2007.12069","repositories_listed":1,"syntology":null},{"url":"/paper/blind-source-extraction-based-on-multi","slug":"blind-source-extraction-based-on-multi","title":"Target Speech Extraction Based on Blind Source Separation and X-vector-based Speaker Selection Trained with Data Augmentation","date":"2020-05-16","arxiv_id":"2005.07976","repositories_listed":1,"syntology":null},{"url":"/paper/deep-normalization-for-speaker-vectors","slug":"deep-normalization-for-speaker-vectors","title":"Deep Normalization for Speaker Vectors","date":"2020-04-07","arxiv_id":"2004.04095","repositories_listed":1,"syntology":null},{"url":"/paper/universal-adversarial-perturbations-2","slug":"universal-adversarial-perturbations-2","title":"Universal Adversarial Perturbations Generative Network for Speaker Recognition","date":"2020-04-07","arxiv_id":"2004.03428","repositories_listed":1,"syntology":null},{"url":"/paper/meta-learning-for-short-utterance-speaker","slug":"meta-learning-for-short-utterance-speaker","title":"Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs","date":"2020-04-06","arxiv_id":"2004.02863","repositories_listed":1,"syntology":null},{"url":"/paper/an-open-set-recognition-and-few-shot-learning","slug":"an-open-set-recognition-and-few-shot-learning","title":"An Open-set Recognition and Few-Shot Learning Dataset for Audio Event Classification in Domestic Environments","date":"2020-02-26","arxiv_id":"2002.11561","repositories_listed":1,"syntology":null},{"url":"/paper/nplda-a-deep-neural-plda-model-for-speaker","slug":"nplda-a-deep-neural-plda-model-for-speaker","title":"NPLDA: A Deep Neural PLDA Model for Speaker Verification","date":"2020-02-10","arxiv_id":"2002.03562","repositories_listed":1,"syntology":null},{"url":"/paper/robust-speaker-recognition-using-unsupervised","slug":"robust-speaker-recognition-using-unsupervised","title":"Robust speaker recognition using unsupervised adversarial invariance","date":"2019-11-03","arxiv_id":"1911.00940","repositories_listed":1,"syntology":null},{"url":"/paper/who-is-real-bob-adversarial-attacks-on","slug":"who-is-real-bob-adversarial-attacks-on","title":"Who is Real Bob? Adversarial Attacks on Speaker Recognition Systems","date":"2019-11-03","arxiv_id":"1911.01840","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/who-is-real-bob-adversarial-attacks-on#ran","syntology_url":"https://syntology.ai/paper/1911.01840","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.01840"}},"official":null}},{"url":"/paper/delving-into-voxceleb-environment-invariant","slug":"delving-into-voxceleb-environment-invariant","title":"Delving into VoxCeleb: environment invariant speaker recognition","date":"2019-10-24","arxiv_id":"1910.11238","repositories_listed":1,"syntology":null},{"url":"/paper/latent-space-representation-for-multi-target","slug":"latent-space-representation-for-multi-target","title":"Latent space representation for multi-target speaker detection and identification with a sparse dataset using Triplet neural networks","date":"2019-10-01","arxiv_id":"1910.01463","repositories_listed":1,"syntology":null},{"url":"/paper/contextual-phonetic-pretraining-for-end-to","slug":"contextual-phonetic-pretraining-for-end-to","title":"BERTphone: Phonetically-Aware Encoder Representations for Utterance-Level Speaker and Language Recognition","date":"2019-06-30","arxiv_id":"1907.00457","repositories_listed":1,"syntology":null},{"url":"/paper/additive-margin-sincnet-for-speaker","slug":"additive-margin-sincnet-for-speaker","title":"Additive Margin SincNet for Speaker Recognition","date":"2019-01-28","arxiv_id":"1901.10826","repositories_listed":1,"syntology":null}],"syntology_records":18,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/speaker-recognition-on-voxceleb1","since_archive":"/sota/speaker-recognition-on-voxceleb1#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":17,"papers_where_code_ran_first_page":"/task/speaker-recognition/papers/ran/1","papers_where_code_ran_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.","pages":[{"order":"archive","page":2,"of":5,"url":"/task/speaker-recognition/papers/2","json":"/task/speaker-recognition/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/task/speaker-recognition/papers/3","json":"/task/speaker-recognition/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/task/speaker-recognition/papers/4","json":"/task/speaker-recognition/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/task/speaker-recognition/papers/5","json":"/task/speaker-recognition/papers/5.json","rows":35},{"order":"ran","page":1,"of":1,"url":"/task/speaker-recognition/papers/ran/1","json":"/task/speaker-recognition/papers/ran/1.json","rows":17}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"5140e047b35c1743456ac7725be805a37786d265e7411077a0d77277e15333b2","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}