{"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-verification","name":"Speaker Verification","slug":"speaker-verification","description_markdown":"Speaker verification is the verifying the identity of a person from characteristics of the voice.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Contrastive-Predictive-Coding-PyTorch\r\n](https://github.com/jefflai108/Contrastive-Predictive-Coding-PyTorch) )</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":746,"papers_with_code":200,"benchmarks":12,"benchmark_tables_in_archive":12,"benchmark_tables_shown":12,"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":12,"subtasks":3,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/speaker-verification-on-voxceleb","slug":"speaker-verification-on-voxceleb","dataset":"VoxCeleb","dataset_url":"/dataset/voxceleb1","rows_in_archive":21,"metrics":["EER"],"first_row_in_archive_order":{"model":"SimAM-ResNet100","paper_title":"VoxBlink2: A 100K+ Speaker Recognition Corpus and the Open-Set Speaker-Identification Benchmark","paper_url":"/paper/voxblink2-a-100k-speaker-recognition-corpus","paper_date":"2024-07-16","arxiv_id":"2407.11510","code_links":[{"title":"wenet-e2e/wespeaker","url":"https://github.com/wenet-e2e/wespeaker"}],"syntology":null}},{"leaderboard":"/sota/speaker-verification-on-voxceleb1","slug":"speaker-verification-on-voxceleb1","dataset":"VoxCeleb1","dataset_url":"/dataset/voxceleb1","rows_in_archive":16,"metrics":["EER"],"first_row_in_archive_order":{"model":"ReDimNet-B6-SF2-LM-ASNorm (15.0M)","paper_title":"Reshape Dimensions Network for Speaker Recognition","paper_url":"/paper/reshape-dimensions-network-for-speaker-1","paper_date":"2024-07-25","arxiv_id":"2407.18223","code_links":[{"title":"IDRnD/ReDimNet","url":"https://github.com/IDRnD/ReDimNet"}],"syntology":null}},{"leaderboard":"/sota/speaker-verification-on-callhome","slug":"speaker-verification-on-callhome","dataset":"CALLHOME","dataset_url":"/dataset/callhome-american-english-speech","rows_in_archive":2,"metrics":["Cosine EER"],"first_row_in_archive_order":{"model":"GE2E","paper_title":"Generalized End-to-End Loss for Speaker Verification","paper_url":"/paper/generalized-end-to-end-loss-for-speaker","paper_date":"2017-10-28","arxiv_id":"1710.10467","code_links":[{"title":"CorentinJ/Real-Time-Voice-Cloning","url":"https://github.com/CorentinJ/Real-Time-Voice-Cloning"},{"title":"coqui-ai/TTS","url":"https://github.com/coqui-ai/TTS"},{"title":"PaddlePaddle/PaddleSpeech","url":"https://github.com/PaddlePaddle/PaddleSpeech"},{"title":"resemble-ai/Resemblyzer","url":"https://github.com/resemble-ai/Resemblyzer"},{"title":"HarryVolek/PyTorch_Speaker_Verification","url":"https://github.com/HarryVolek/PyTorch_Speaker_Verification"},{"title":"google/speaker-id","url":"https://github.com/google/speaker-id/tree/master/lingvo"},{"title":"JanhHyun/Speaker_Verification","url":"https://github.com/JanhHyun/Speaker_Verification"},{"title":"Janghyun1230/Speaker_Verification","url":"https://github.com/Janghyun1230/Speaker_Verification"},{"title":"yistLin/dvector","url":"https://github.com/yistLin/dvector"},{"title":"rf5/simple-speaker-embedding","url":"https://github.com/rf5/simple-speaker-embedding"},{"title":"cvqluu/GE2E-Loss","url":"https://github.com/cvqluu/GE2E-Loss"},{"title":"Suhee05/Text-Independent-Speaker-Verification","url":"https://github.com/Suhee05/Text-Independent-Speaker-Verification"},{"title":"Aurora11111/voiceprint","url":"https://github.com/Aurora11111/voiceprint"},{"title":"Aurora11111/speaker-recognition-pytorch","url":"https://github.com/Aurora11111/speaker-recognition-pytorch"},{"title":"muskang48/Speaker-Diarization","url":"https://github.com/muskang48/Speaker-Diarization"},{"title":"tigthor/Voice-Cloning-AI","url":"https://github.com/tigthor/Voice-Cloning-AI"},{"title":"piotrkawa/audio-deepfake-source-tracing","url":"https://github.com/piotrkawa/audio-deepfake-source-tracing"},{"title":"JeffT13/rd-diarization","url":"https://github.com/JeffT13/rd-diarization"},{"title":"gkv856/speaker_embedding_GE2E_loss","url":"https://github.com/gkv856/speaker_embedding_GE2E_loss"},{"title":"dalonlobo/diarization-experiments","url":"https://github.com/dalonlobo/diarization-experiments"},{"title":"luomingshuang/GE2E-SV-TI-Voxceleb-LMS","url":"https://github.com/luomingshuang/GE2E-SV-TI-Voxceleb-LMS"},{"title":"yui-mhcp/base_dl_project","url":"https://github.com/yui-mhcp/base_dl_project"},{"title":"luomingshuang/GE2E-SV-TI-Timit-LMS","url":"https://github.com/luomingshuang/GE2E-SV-TI-Timit-LMS"},{"title":"aijianiula0601/ge2eloss-svf","url":"https://github.com/aijianiula0601/ge2eloss-svf"},{"title":"luomingshuang/GE2E-SV-TI-thchs30-LMS","url":"https://github.com/luomingshuang/GE2E-SV-TI-thchs30-LMS"},{"title":"JeffT13/VoiceEncoder","url":"https://github.com/JeffT13/VoiceEncoder"},{"title":"hanqingguo/GE2E","url":"https://github.com/hanqingguo/GE2E"},{"title":"zhangmin4215/PyTorch_Speaker_Verification","url":"https://github.com/zhangmin4215/PyTorch_Speaker_Verification"},{"title":"icewing1996/baseline","url":"https://github.com/icewing1996/baseline"},{"title":"luomingshuang/GE2E-SV-TI-Chinese-LMS","url":"https://github.com/luomingshuang/GE2E-SV-TI-Chinese-LMS"}],"syntology":{"n":27,"n_ran":19,"n_constructed":0,"n_ran_checked":17,"n_instrument":2,"n_unverified":8,"n_honours":1,"n_violates":1,"n_no_contract":15,"n_pointer_only":2,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 1 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/generalized-end-to-end-loss-for-speaker#ran","syntology_url":"https://syntology.ai/paper/1710.10467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10467"}},"official":{"repos":["google/speaker-id"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/speaker-verification-on-cn-celeb","slug":"speaker-verification-on-cn-celeb","dataset":"CN-CELEB","dataset_url":"/dataset/cn-celeb","rows_in_archive":2,"metrics":["EER"],"first_row_in_archive_order":{"model":"X-Vectors with Attention Backend","paper_title":"Attention Back-end for Automatic Speaker Verification with Multiple Enrollment Utterances","paper_url":"/paper/attention-back-end-for-automatic-speaker","paper_date":"2021-04-04","arxiv_id":"2104.01541","code_links":[{"title":"nii-yamagishilab/Attention_Backend_for_ASV","url":"https://github.com/nii-yamagishilab/Attention_Backend_for_ASV"}],"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/attention-back-end-for-automatic-speaker#ran","syntology_url":"https://syntology.ai/paper/2104.01541","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.01541"}},"official":{"repos":["nii-yamagishilab/Attention_Backend_for_ASV"],"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"]}}}},{"leaderboard":"/sota/speaker-verification-on-asvspoof-2019-la","slug":"speaker-verification-on-asvspoof-2019-la","dataset":"ASVspoof 2019 - LA","dataset_url":null,"rows_in_archive":1,"metrics":["minDCF"],"first_row_in_archive_order":{"model":"ECAPA-TDNN","paper_title":"Tandem spoofing-robust automatic speaker verification based on time-domain embeddings","paper_url":"/paper/tandem-spoofing-robust-automatic-speaker","paper_date":"2024-12-22","arxiv_id":"2412.17133","code_links":[],"syntology":null}},{"leaderboard":"/sota/speaker-verification-on-vibravox-forehead","slug":"speaker-verification-on-vibravox-forehead","dataset":"VibraVox (forehead accelerometer)","dataset_url":"/dataset/vibravox-forehead-accelerometer","rows_in_archive":1,"metrics":["Test EER","Test min-DCF"],"first_row_in_archive_order":{"model":"ECAPA2","paper_title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","paper_url":"/paper/vibravox-a-dataset-of-french-speech-captured","paper_date":"2024-07-16","arxiv_id":"2407.11828","code_links":[{"title":"jhauret/vibravox","url":"https://github.com/jhauret/vibravox"}],"syntology":null}},{"leaderboard":"/sota/speaker-verification-on-vibravox-headset","slug":"speaker-verification-on-vibravox-headset","dataset":"VibraVox (headset microphone)","dataset_url":"/dataset/vibravox-headset-microphone","rows_in_archive":1,"metrics":["Test EER","Test min-DCF"],"first_row_in_archive_order":{"model":"ECAPA2","paper_title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","paper_url":"/paper/vibravox-a-dataset-of-french-speech-captured","paper_date":"2024-07-16","arxiv_id":"2407.11828","code_links":[{"title":"jhauret/vibravox","url":"https://github.com/jhauret/vibravox"}],"syntology":null}},{"leaderboard":"/sota/speaker-verification-on-vibravox-rigid-in-ear","slug":"speaker-verification-on-vibravox-rigid-in-ear","dataset":"VibraVox (rigid in-ear microphone)","dataset_url":"/dataset/vibravox","rows_in_archive":1,"metrics":["Test EER","Test min-DCF"],"first_row_in_archive_order":{"model":"ECAPA2","paper_title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","paper_url":"/paper/vibravox-a-dataset-of-french-speech-captured","paper_date":"2024-07-16","arxiv_id":"2407.11828","code_links":[{"title":"jhauret/vibravox","url":"https://github.com/jhauret/vibravox"}],"syntology":null}},{"leaderboard":"/sota/speaker-verification-on-vibravox-soft-in-ear","slug":"speaker-verification-on-vibravox-soft-in-ear","dataset":"VibraVox (soft in-ear microphone)","dataset_url":"/dataset/vibravox-soft-in-ear-microphone","rows_in_archive":1,"metrics":["Test EER","Test min-DCF"],"first_row_in_archive_order":{"model":"ECAPA2","paper_title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","paper_url":"/paper/vibravox-a-dataset-of-french-speech-captured","paper_date":"2024-07-16","arxiv_id":"2407.11828","code_links":[{"title":"jhauret/vibravox","url":"https://github.com/jhauret/vibravox"}],"syntology":null}},{"leaderboard":"/sota/speaker-verification-on-vibravox-temple","slug":"speaker-verification-on-vibravox-temple","dataset":"VibraVox (temple vibration pickup)","dataset_url":"/dataset/vibravox-temple-vibration-pickup","rows_in_archive":1,"metrics":["Test EER","Test min-DCF"],"first_row_in_archive_order":{"model":"ECAPA2","paper_title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","paper_url":"/paper/vibravox-a-dataset-of-french-speech-captured","paper_date":"2024-07-16","arxiv_id":"2407.11828","code_links":[{"title":"jhauret/vibravox","url":"https://github.com/jhauret/vibravox"}],"syntology":null}},{"leaderboard":"/sota/speaker-verification-on-vibravox-throat","slug":"speaker-verification-on-vibravox-throat","dataset":"VibraVox (throat microphone)","dataset_url":"/dataset/vibravox-throat-microphone","rows_in_archive":1,"metrics":["Test EER","Test min-DCF"],"first_row_in_archive_order":{"model":"ECAPA2","paper_title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","paper_url":"/paper/vibravox-a-dataset-of-french-speech-captured","paper_date":"2024-07-16","arxiv_id":"2407.11828","code_links":[{"title":"jhauret/vibravox","url":"https://github.com/jhauret/vibravox"}],"syntology":null}},{"leaderboard":"/sota/speaker-verification-on-voxceleb2","slug":"speaker-verification-on-voxceleb2","dataset":"VoxCeleb2","dataset_url":"/dataset/voxceleb2","rows_in_archive":1,"metrics":["EER"],"first_row_in_archive_order":{"model":"ResNet-50","paper_title":"VoxCeleb2: Deep Speaker Recognition","paper_url":"/paper/voxceleb2-deep-speaker-recognition","paper_date":"2018-06-14","arxiv_id":"1806.05622","code_links":[{"title":"a-nagrani/VGGVox","url":"https://github.com/a-nagrani/VGGVox"},{"title":"MainRo/deep-speaker","url":"https://github.com/MainRo/deep-speaker"}],"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}}}],"datasets":[{"url":"/dataset/voxceleb1","name":"VoxCeleb1","full_name":"VoxCeleb1","num_papers_in_archive":680},{"url":"/dataset/voxceleb2","name":"VoxCeleb2","full_name":"VoxCeleb2","num_papers_in_archive":564},{"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/callhome-american-english-speech","name":"CALLHOME American English Speech","full_name":"","num_papers_in_archive":11},{"url":"/dataset/evi","name":"EVI","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vibravox-forehead-accelerometer","name":"VibraVox (forehead accelerometer)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vibravox-headset-microphone","name":"VibraVox (headset microphone)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vibravox","name":"VibraVox (rigid in-ear microphone)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vibravox-soft-in-ear-microphone","name":"VibraVox (soft in-ear microphone)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vibravox-temple-vibration-pickup","name":"VibraVox (temple vibration pickup)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vibravox-throat-microphone","name":"VibraVox (throat microphone)","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/audio-deepfake-detection","name":"Audio Deepfake Detection"},{"url":"/task/text-dependent-speaker-verification","name":"Text-Dependent Speaker Verification"},{"url":"/task/text-independent-speaker-verification","name":"Text-Independent Speaker Verification"}],"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":8,"rows_per_page":100,"shown":100,"of":746,"of_with_code":200,"tagged_in_all":746,"counts":{"archive_papers_tagged":746,"with_a_code_link":200,"where_syntology_ran_a_sample":29,"not_listed_spam_title":0,"listed":746,"listed_where_code_ran":29,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":23,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":23,"listed_every_run_a_failure_of_syntologys_instrument":6,"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/generalized-end-to-end-loss-for-speaker","slug":"generalized-end-to-end-loss-for-speaker","title":"Generalized End-to-End Loss for Speaker Verification","date":"2017-10-28","arxiv_id":"1710.10467","repositories_listed":30,"syntology":{"n":27,"n_ran":19,"n_constructed":0,"n_ran_checked":17,"n_instrument":2,"n_unverified":8,"n_honours":1,"n_violates":1,"n_no_contract":15,"n_pointer_only":2,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 1 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/generalized-end-to-end-loss-for-speaker#ran","syntology_url":"https://syntology.ai/paper/1710.10467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10467"}},"official":{"repos":["google/speaker-id"],"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/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/transfer-learning-from-speaker-verification","slug":"transfer-learning-from-speaker-verification","title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","date":"2018-06-12","arxiv_id":"1806.04558","repositories_listed":11,"syntology":null},{"url":"/paper/defense-for-black-box-attacks-on-anti","slug":"defense-for-black-box-attacks-on-anti","title":"Defense for Black-box Attacks on Anti-spoofing Models by Self-Supervised Learning","date":"2020-06-05","arxiv_id":"2006.03214","repositories_listed":6,"syntology":null},{"url":"/paper/rawnet-advanced-end-to-end-deep-neural","slug":"rawnet-advanced-end-to-end-deep-neural","title":"RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification","date":"2019-04-17","arxiv_id":"1904.08104","repositories_listed":5,"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/rawnet-advanced-end-to-end-deep-neural#ran","syntology_url":"https://syntology.ai/paper/1904.08104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08104"}},"official":{"repos":["Jungjee/RawNet"],"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/text-independent-speaker-verification-using","slug":"text-independent-speaker-verification-using","title":"Text-Independent Speaker Verification Using 3D Convolutional Neural Networks","date":"2017-05-26","arxiv_id":"1705.09422","repositories_listed":5,"syntology":null},{"url":"/paper/asvspoof-2019-future-horizons-in-spoofed-and","slug":"asvspoof-2019-future-horizons-in-spoofed-and","title":"ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection","date":"2019-04-14","arxiv_id":"1904.05441","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"6 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/asvspoof-2019-future-horizons-in-spoofed-and#ran","syntology_url":"https://syntology.ai/paper/1904.05441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.05441"}},"official":null}},{"url":"/paper/an-unsupervised-autoregressive-model-for","slug":"an-unsupervised-autoregressive-model-for","title":"An Unsupervised Autoregressive Model for Speech Representation Learning","date":"2019-04-05","arxiv_id":"1904.03240","repositories_listed":4,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-unsupervised-autoregressive-model-for#ran","syntology_url":"https://syntology.ai/paper/1904.03240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.03240"}},"official":null}},{"url":"/paper/speaker-diarization-with-lstm","slug":"speaker-diarization-with-lstm","title":"Speaker Diarization with LSTM","date":"2017-10-28","arxiv_id":"1710.10468","repositories_listed":4,"syntology":null},{"url":"/paper/automatic-speaker-verification-spoofing-and","slug":"automatic-speaker-verification-spoofing-and","title":"Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation","date":"2022-02-24","arxiv_id":"2202.12233","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/automatic-speaker-verification-spoofing-and#ran","syntology_url":"https://syntology.ai/paper/2202.12233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.12233"}},"official":null}},{"url":"/paper/an-empirical-study-on-channel-effects-for","slug":"an-empirical-study-on-channel-effects-for","title":"An Empirical Study on Channel Effects for Synthetic Voice Spoofing Countermeasure Systems","date":"2021-04-03","arxiv_id":"2104.01320","repositories_listed":3,"syntology":{"n":18,"n_ran":14,"n_constructed":0,"n_ran_checked":9,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":5,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/an-empirical-study-on-channel-effects-for#ran","syntology_url":"https://syntology.ai/paper/2104.01320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.01320"}},"official":{"repos":["yzyouzhang/Empirical-Channel-CM"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/one-class-learning-towards-generalized-voice-1","slug":"one-class-learning-towards-generalized-voice-1","title":"One-class learning towards generalized voice spoofing detection","date":"2020-10-27","arxiv_id":"2010.13995","repositories_listed":3,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/one-class-learning-towards-generalized-voice-1#ran","syntology_url":"https://syntology.ai/paper/2010.13995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.13995"}},"official":{"repos":["yzyouzhang/AIR-ASVspoof"],"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/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/ludwig-a-type-based-declarative-deep-learning","slug":"ludwig-a-type-based-declarative-deep-learning","title":"Ludwig: a type-based declarative deep learning toolbox","date":"2019-09-17","arxiv_id":"1909.07930","repositories_listed":3,"syntology":null},{"url":"/paper/rvad-an-unsupervised-segment-based-robust","slug":"rvad-an-unsupervised-segment-based-robust","title":"rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method","date":"2019-06-09","arxiv_id":"1906.03588","repositories_listed":3,"syntology":null},{"url":"/paper/unsupervised-learning-of-disentangled-and","slug":"unsupervised-learning-of-disentangled-and","title":"Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data","date":"2017-09-22","arxiv_id":"1709.07902","repositories_listed":3,"syntology":null},{"url":"/paper/end-to-end-text-dependent-speaker","slug":"end-to-end-text-dependent-speaker","title":"End-to-End Text-Dependent Speaker Verification","date":"2015-09-27","arxiv_id":"1509.08062","repositories_listed":3,"syntology":null},{"url":"/paper/self-distillation-prototypes-network-learning","slug":"self-distillation-prototypes-network-learning","title":"Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision","date":"2024-06-17","arxiv_id":"2406.11169","repositories_listed":2,"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/arbitrary-discrete-fourier-analysis-and-its","slug":"arbitrary-discrete-fourier-analysis-and-its","title":"Advanced Signal Analysis in Detecting Replay Attacks for Automatic Speaker Verification Systems","date":"2024-03-02","arxiv_id":"2403.01130","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/pairwise-similarity-learning-is-simple-1","slug":"pairwise-similarity-learning-is-simple-1","title":"Pairwise Similarity Learning is SimPLE","date":"2023-10-13","arxiv_id":"2310.09449","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":1,"n_ran_checked":4,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"8 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pairwise-similarity-learning-is-simple-1#ran","syntology_url":"https://syntology.ai/paper/2310.09449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09449"}},"official":{"repos":["ydwen/opensphere"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ensemble-distillation-network-learning-robust","slug":"ensemble-distillation-network-learning-robust","title":"Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision","date":"2023-08-05","arxiv_id":"2308.02774","repositories_listed":2,"syntology":null},{"url":"/paper/an-enhanced-res2net-with-local-and-global","slug":"an-enhanced-res2net-with-local-and-global","title":"An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verification","date":"2023-05-22","arxiv_id":"2305.12838","repositories_listed":2,"syntology":null},{"url":"/paper/cryceleb-a-speaker-verification-dataset-based","slug":"cryceleb-a-speaker-verification-dataset-based","title":"CryCeleb: A Speaker Verification Dataset Based on Infant Cry Sounds","date":"2023-05-01","arxiv_id":"2305.00969","repositories_listed":2,"syntology":null},{"url":"/paper/samo-speaker-attractor-multi-center-one-class","slug":"samo-speaker-attractor-multi-center-one-class","title":"SAMO: Speaker Attractor Multi-Center One-Class Learning for Voice Anti-Spoofing","date":"2022-11-04","arxiv_id":"2211.02718","repositories_listed":2,"syntology":null},{"url":"/paper/convnext-based-neural-network-for-anti","slug":"convnext-based-neural-network-for-anti","title":"ConvNeXt Based Neural Network for Audio Anti-Spoofing","date":"2022-09-14","arxiv_id":"2209.06434","repositories_listed":2,"syntology":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/the-voiceprivacy-2022-challenge-evaluation","slug":"the-voiceprivacy-2022-challenge-evaluation","title":"The VoicePrivacy 2022 Challenge Evaluation Plan","date":"2022-03-23","arxiv_id":"2203.12468","repositories_listed":2,"syntology":null},{"url":"/paper/a-3-t-alignment-aware-acoustic-and-text","slug":"a-3-t-alignment-aware-acoustic-and-text","title":"A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing","date":"2022-03-18","arxiv_id":"2203.09690","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/a-3-t-alignment-aware-acoustic-and-text#ran","syntology_url":"https://syntology.ai/paper/2203.09690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09690"}},"official":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/rawboost-a-raw-data-boosting-and-augmentation","slug":"rawboost-a-raw-data-boosting-and-augmentation","title":"RawBoost: A Raw Data Boosting and Augmentation Method applied to Automatic Speaker Verification Anti-Spoofing","date":"2021-11-08","arxiv_id":"2111.04433","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rawboost-a-raw-data-boosting-and-augmentation#ran","syntology_url":"https://syntology.ai/paper/2111.04433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.04433"}},"official":{"repos":["TakHemlata/RawBoost-antispoofing"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/titanet-neural-model-for-speaker","slug":"titanet-neural-model-for-speaker","title":"TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context","date":"2021-10-08","arxiv_id":"2110.04410","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/titanet-neural-model-for-speaker#ran","syntology_url":"https://syntology.ai/paper/2110.04410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04410"}},"official":{"repos":["NVIDIA/NeMo"],"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/sveva-fair-a-framework-for-evaluating","slug":"sveva-fair-a-framework-for-evaluating","title":"SVEva Fair: A Framework for Evaluating Fairness in Speaker Verification","date":"2021-07-26","arxiv_id":"2107.12049","repositories_listed":2,"syntology":null},{"url":"/paper/channel-wise-gated-res2net-towards-robust","slug":"channel-wise-gated-res2net-towards-robust","title":"Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attacks","date":"2021-07-19","arxiv_id":"2107.08803","repositories_listed":2,"syntology":null},{"url":"/paper/fragmentvc-any-to-any-voice-conversion-by-end","slug":"fragmentvc-any-to-any-voice-conversion-by-end","title":"FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention","date":"2020-10-27","arxiv_id":"2010.14150","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/fragmentvc-any-to-any-voice-conversion-by-end#ran","syntology_url":"https://syntology.ai/paper/2010.14150","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.14150"}},"official":{"repos":["yistLin/FragmentVC"],"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":["listed","official"]}}},{"url":"/paper/backdoor-attack-against-speaker-verification","slug":"backdoor-attack-against-speaker-verification","title":"Backdoor Attack against Speaker Verification","date":"2020-10-22","arxiv_id":"2010.11607","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/backdoor-attack-against-speaker-verification#ran","syntology_url":"https://syntology.ai/paper/2010.11607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11607"}},"official":{"repos":["zhaitongqing233/Backdoor-attack-against-speaker-verification"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/improved-rawnet-with-filter-wise-rescaling","slug":"improved-rawnet-with-filter-wise-rescaling","title":"Improved RawNet with Feature Map Scaling for Text-independent Speaker Verification using Raw Waveforms","date":"2020-04-01","arxiv_id":"2004.00526","repositories_listed":2,"syntology":null},{"url":"/paper/a-speaker-verification-backend-for-improved","slug":"a-speaker-verification-backend-for-improved","title":"A Speaker Verification Backend for Improved Calibration Performance across Varying Conditions","date":"2020-02-05","arxiv_id":"2002.03802","repositories_listed":2,"syntology":null},{"url":"/paper/adversarial-attacks-on-gmm-i-vector-based","slug":"adversarial-attacks-on-gmm-i-vector-based","title":"Adversarial Attacks on GMM i-vector based Speaker Verification Systems","date":"2019-11-08","arxiv_id":"1911.03078","repositories_listed":2,"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/adversarial-attacks-on-gmm-i-vector-based#ran","syntology_url":"https://syntology.ai/paper/1911.03078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03078"}},"official":{"repos":["lixucuhk/adversarial-attack-on-GMM-i-vector-based-speaker-verification-systems"],"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/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/delta-a-deep-learning-based-language","slug":"delta-a-deep-learning-based-language","title":"DELTA: A DEep learning based Language Technology plAtform","date":"2019-08-02","arxiv_id":"1908.01853","repositories_listed":2,"syntology":null},{"url":"/paper/multiobjective-optimization-training-of-plda","slug":"multiobjective-optimization-training-of-plda","title":"Multiobjective Optimization Training of PLDA for Speaker Verification","date":"2018-08-25","arxiv_id":"1808.08344","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/scalable-factorized-hierarchical-variational","slug":"scalable-factorized-hierarchical-variational","title":"Scalable Factorized Hierarchical Variational Autoencoder Training","date":"2018-04-09","arxiv_id":"1804.03201","repositories_listed":2,"syntology":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/3d-convolutional-neural-networks-for-cross","slug":"3d-convolutional-neural-networks-for-cross","title":"3D Convolutional Neural Networks for Cross Audio-Visual Matching Recognition","date":"2017-06-18","arxiv_id":"1706.05739","repositories_listed":2,"syntology":null},{"url":"/paper/pushing-the-performance-of-synthetic-speech","slug":"pushing-the-performance-of-synthetic-speech","title":"Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Models","date":"2025-06-17","arxiv_id":"2506.14153","repositories_listed":1,"syntology":null},{"url":"/paper/asvspoof2019-vs-asvspoof5-assessment-and","slug":"asvspoof2019-vs-asvspoof5-assessment-and","title":"ASVspoof2019 vs. ASVspoof5: Assessment and Comparison","date":"2025-05-21","arxiv_id":"2505.15911","repositories_listed":1,"syntology":null},{"url":"/paper/pushing-the-frontiers-of-self-distillation","slug":"pushing-the-frontiers-of-self-distillation","title":"Pushing the Frontiers of Self-Distillation Prototypes Network with Dimension Regularization and Score Normalization","date":"2025-05-20","arxiv_id":"2505.13826","repositories_listed":1,"syntology":null},{"url":"/paper/ssps-self-supervised-positive-sampling-for","slug":"ssps-self-supervised-positive-sampling-for","title":"SSPS: Self-Supervised Positive Sampling for Robust Self-Supervised Speaker Verification","date":"2025-05-20","arxiv_id":"2505.14561","repositories_listed":1,"syntology":null},{"url":"/paper/cbw-towards-dataset-ownership-verification","slug":"cbw-towards-dataset-ownership-verification","title":"CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking","date":"2025-03-02","arxiv_id":"2503.05794","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-frameworks-for-speaker","slug":"self-supervised-frameworks-for-speaker","title":"Self-Supervised Frameworks for Speaker Verification via Bootstrapped Positive Sampling","date":"2025-01-29","arxiv_id":"2501.17772","repositories_listed":1,"syntology":null},{"url":"/paper/sef-pnet-speaker-encoder-free-personalized","slug":"sef-pnet-speaker-encoder-free-personalized","title":"SEF-PNet: Speaker Encoder-Free Personalized Speech Enhancement with Local and Global Contexts Aggregation","date":"2025-01-20","arxiv_id":"2501.11274","repositories_listed":1,"syntology":null},{"url":"/paper/expo-explainable-phonetic-trait-oriented","slug":"expo-explainable-phonetic-trait-oriented","title":"ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification","date":"2025-01-10","arxiv_id":"2501.05729","repositories_listed":1,"syntology":null},{"url":"/paper/spectral-aware-low-rank-adaptation-for","slug":"spectral-aware-low-rank-adaptation-for","title":"Spectral-Aware Low-Rank Adaptation for Speaker Verification","date":"2025-01-07","arxiv_id":"2501.03829","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-unauthorized-speech-synthesis-for","slug":"mitigating-unauthorized-speech-synthesis-for","title":"Mitigating Unauthorized Speech Synthesis for Voice Protection","date":"2024-10-28","arxiv_id":"2410.20742","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mitigating-unauthorized-speech-synthesis-for#ran","syntology_url":"https://syntology.ai/paper/2410.20742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20742"}},"official":{"repos":["wxzyd123/pivotal_objective_perturbation"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-first-voiceprivacy-attacker-challenge","slug":"the-first-voiceprivacy-attacker-challenge","title":"The First VoicePrivacy Attacker Challenge Evaluation Plan","date":"2024-10-09","arxiv_id":"2410.07428","repositories_listed":1,"syntology":null},{"url":"/paper/universal-pooling-method-of-multi-layer","slug":"universal-pooling-method-of-multi-layer","title":"Universal Pooling Method of Multi-layer Features from Pretrained Models for Speaker Verification","date":"2024-09-12","arxiv_id":"2409.07770","repositories_listed":1,"syntology":null},{"url":"/paper/malacopula-adversarial-automatic-speaker","slug":"malacopula-adversarial-automatic-speaker","title":"Malacopula: adversarial automatic speaker verification attacks using a neural-based generalised Hammerstein model","date":"2024-08-17","arxiv_id":"2408.09300","repositories_listed":1,"syntology":null},{"url":"/paper/multi-stage-face-voice-association-learning","slug":"multi-stage-face-voice-association-learning","title":"Multi-Stage Face-Voice Association Learning with Keynote Speaker Diarization","date":"2024-07-25","arxiv_id":"2407.17902","repositories_listed":1,"syntology":null},{"url":"/paper/vibravox-a-dataset-of-french-speech-captured","slug":"vibravox-a-dataset-of-french-speech-captured","title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","date":"2024-07-16","arxiv_id":"2407.11828","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/listen-and-speak-fairly-a-study-on-semantic","slug":"listen-and-speak-fairly-a-study-on-semantic","title":"Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models","date":"2024-07-09","arxiv_id":"2407.06957","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-and-improving-scoring-fusion-for","slug":"revisiting-and-improving-scoring-fusion-for","title":"Revisiting and Improving Scoring Fusion for Spoofing-aware Speaker Verification Using Compositional Data Analysis","date":"2024-06-16","arxiv_id":"2406.10836","repositories_listed":1,"syntology":null},{"url":"/paper/robust-channel-learning-for-large-scale-radio","slug":"robust-channel-learning-for-large-scale-radio","title":"Robust Channel Learning for Large-Scale Radio Speaker Verification","date":"2024-06-16","arxiv_id":"2406.10956","repositories_listed":1,"syntology":null},{"url":"/paper/mr-rawnet-speaker-verification-system-with","slug":"mr-rawnet-speaker-verification-system-with","title":"MR-RawNet: Speaker verification system with multiple temporal resolutions for variable duration utterances using raw waveforms","date":"2024-06-11","arxiv_id":"2406.07103","repositories_listed":1,"syntology":null},{"url":"/paper/towards-supervised-performance-on-speaker","slug":"towards-supervised-performance-on-speaker","title":"Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models","date":"2024-06-04","arxiv_id":"2406.02285","repositories_listed":1,"syntology":null},{"url":"/paper/additive-margin-in-contrastive-self","slug":"additive-margin-in-contrastive-self","title":"Additive Margin in Contrastive Self-Supervised Frameworks to Learn Discriminative Speaker Representations","date":"2024-04-23","arxiv_id":"2404.14913","repositories_listed":1,"syntology":null},{"url":"/paper/kunqudb-an-attempt-for-speaker-verification","slug":"kunqudb-an-attempt-for-speaker-verification","title":"KunquDB: An Attempt for Speaker Verification in the Chinese Opera Scenario","date":"2024-03-20","arxiv_id":"2403.13356","repositories_listed":1,"syntology":null},{"url":"/paper/a-dcf-an-architecture-agnostic-metric-with","slug":"a-dcf-an-architecture-agnostic-metric-with","title":"a-DCF: an architecture agnostic metric with application to spoofing-robust speaker verification","date":"2024-03-03","arxiv_id":"2403.01355","repositories_listed":1,"syntology":null},{"url":"/paper/childaugment-data-augmentation-methods-for","slug":"childaugment-data-augmentation-methods-for","title":"ChildAugment: Data Augmentation Methods for Zero-Resource Children's Speaker Verification","date":"2024-02-23","arxiv_id":"2402.15214","repositories_listed":1,"syntology":null},{"url":"/paper/singer-identity-representation-learning-using-1","slug":"singer-identity-representation-learning-using-1","title":"Singer Identity Representation Learning using Self-Supervised Techniques","date":"2024-01-10","arxiv_id":"2401.05064","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/singer-identity-representation-learning-using-1#ran","syntology_url":"https://syntology.ai/paper/2401.05064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05064"}},"official":{"repos":["SonyCSLParis/ssl-singer-identity"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/vot-revolutionizing-speaker-verification-with","slug":"vot-revolutionizing-speaker-verification-with","title":"A New Perspective on Speaker Verification: Joint Modeling with DFSMN and Transformer","date":"2023-12-28","arxiv_id":"2312.16826","repositories_listed":1,"syntology":null},{"url":"/paper/next-tdnn-modernizing-multi-scale-temporal","slug":"next-tdnn-modernizing-multi-scale-temporal","title":"NeXt-TDNN: Modernizing Multi-Scale Temporal Convolution Backbone for Speaker Verification","date":"2023-12-14","arxiv_id":"2312.08603","repositories_listed":1,"syntology":null},{"url":"/paper/golden-gemini-is-all-you-need-finding-the","slug":"golden-gemini-is-all-you-need-finding-the","title":"Golden Gemini is All You Need: Finding the Sweet Spots for Speaker Verification","date":"2023-12-06","arxiv_id":"2312.03620","repositories_listed":1,"syntology":null},{"url":"/paper/learning-repeatable-speech-embeddings-using","slug":"learning-repeatable-speech-embeddings-using","title":"Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizer","date":"2023-10-25","arxiv_id":"2310.17049","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":0,"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/learning-repeatable-speech-embeddings-using#ran","syntology_url":"https://syntology.ai/paper/2310.17049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17049"}},"official":{"repos":["vigor-jzhang/icc-regularizer"],"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/salmonn-towards-generic-hearing-abilities-for","slug":"salmonn-towards-generic-hearing-abilities-for","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","date":"2023-10-20","arxiv_id":"2310.13289","repositories_listed":1,"syntology":null},{"url":"/paper/haha-pod-an-attempt-for-laughter-based-non","slug":"haha-pod-an-attempt-for-laughter-based-non","title":"Haha-Pod: An Attempt for Laughter-based Non-Verbal Speaker Verification","date":"2023-09-25","arxiv_id":"2309.14109","repositories_listed":1,"syntology":null},{"url":"/paper/diff-sv-a-unified-hierarchical-framework-for","slug":"diff-sv-a-unified-hierarchical-framework-for","title":"Diff-SV: A Unified Hierarchical Framework for Noise-Robust Speaker Verification Using Score-Based Diffusion Probabilistic Models","date":"2023-09-14","arxiv_id":"2309.08320","repositories_listed":1,"syntology":null},{"url":"/paper/pas-partial-additive-speech-data-augmentation","slug":"pas-partial-additive-speech-data-augmentation","title":"PAS: Partial Additive Speech Data Augmentation Method for Noise Robust Speaker Verification","date":"2023-07-20","arxiv_id":"2307.10628","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-binary-classification-loss-for","slug":"exploring-binary-classification-loss-for","title":"Exploring Binary Classification Loss For Speaker Verification","date":"2023-07-17","arxiv_id":"2307.08205","repositories_listed":1,"syntology":null},{"url":"/paper/disentanglement-in-a-gan-for-unconditional","slug":"disentanglement-in-a-gan-for-unconditional","title":"Disentanglement in a GAN for Unconditional Speech Synthesis","date":"2023-07-04","arxiv_id":"2307.01673","repositories_listed":1,"syntology":null},{"url":"/paper/long-term-conversation-analysis-exploring","slug":"long-term-conversation-analysis-exploring","title":"Long-term Conversation Analysis: Exploring Utility and Privacy","date":"2023-06-28","arxiv_id":"2306.16071","repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-of-speech-representations-for-mos","slug":"evaluation-of-speech-representations-for-mos","title":"Evaluation of Speech Representations for MOS prediction","date":"2023-06-16","arxiv_id":"2306.09979","repositories_listed":1,"syntology":null},{"url":"/paper/malafide-a-novel-adversarial-convolutive","slug":"malafide-a-novel-adversarial-convolutive","title":"Malafide: a novel adversarial convolutive noise attack against deepfake and spoofing detection systems","date":"2023-06-13","arxiv_id":"2306.07655","repositories_listed":1,"syntology":null},{"url":"/paper/experimenting-with-additive-margins-for","slug":"experimenting-with-additive-margins-for","title":"Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification","date":"2023-06-06","arxiv_id":"2306.03664","repositories_listed":1,"syntology":null},{"url":"/paper/multi-dataset-co-training-with-sharpness","slug":"multi-dataset-co-training-with-sharpness","title":"Multi-Dataset Co-Training with Sharpness-Aware Optimization for Audio Anti-spoofing","date":"2023-05-31","arxiv_id":"2305.19953","repositories_listed":1,"syntology":null},{"url":"/paper/towards-single-integrated-spoofing-aware","slug":"towards-single-integrated-spoofing-aware","title":"Towards single integrated spoofing-aware speaker verification embeddings","date":"2023-05-30","arxiv_id":"2305.19051","repositories_listed":1,"syntology":null},{"url":"/paper/one-step-knowledge-distillation-and-fine","slug":"one-step-knowledge-distillation-and-fine","title":"One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification","date":"2023-05-27","arxiv_id":"2305.17394","repositories_listed":1,"syntology":null},{"url":"/paper/aca-net-towards-lightweight-speaker","slug":"aca-net-towards-lightweight-speaker","title":"ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention","date":"2023-05-20","arxiv_id":"2305.12121","repositories_listed":1,"syntology":null},{"url":"/paper/bts-e-audio-deepfake-detection-using","slug":"bts-e-audio-deepfake-detection-using","title":"Bts-e: Audio deepfake detection using breathing-talking-silence encoder","date":"2023-05-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dual-stream-time-delay-neural-network-with","slug":"dual-stream-time-delay-neural-network-with","title":"DS-TDNN: Dual-stream Time-delay Neural Network with Global-aware Filter for Speaker Verification","date":"2023-03-20","arxiv_id":"2303.11020","repositories_listed":1,"syntology":null},{"url":"/paper/can-spoofing-countermeasure-and-speaker","slug":"can-spoofing-countermeasure-and-speaker","title":"Can spoofing countermeasure and speaker verification systems be jointly optimised?","date":"2023-03-13","arxiv_id":"2303.07073","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-audio-visual-co-learning-for-text","slug":"cross-modal-audio-visual-co-learning-for-text","title":"Cross-modal Audio-visual Co-learning for Text-independent Speaker Verification","date":"2023-02-22","arxiv_id":"2302.11254","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/cross-modal-information-fusion-for-voice","slug":"cross-modal-information-fusion-for-voice","title":"Cross-modal information fusion for voice spoofing detection","date":"2023-02-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"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/towards-a-unified-conformer-structure-from","slug":"towards-a-unified-conformer-structure-from","title":"Towards A Unified Conformer Structure: from ASR to ASV Task","date":"2022-11-14","arxiv_id":"2211.07201","repositories_listed":1,"syntology":null}],"syntology_records":20,"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":2,"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-verification-on-voxceleb1","since_archive":"/sota/speaker-verification-on-voxceleb1#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/speaker-verification-on-cn-celeb","since_archive":"/sota/speaker-verification-on-cn-celeb#since-judged","papers_judged":2,"placed":0}]},"papers_where_code_ran":29,"papers_where_code_ran_first_page":"/task/speaker-verification/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":8,"url":"/task/speaker-verification/papers/2","json":"/task/speaker-verification/papers/2.json","rows":100},{"order":"archive","page":3,"of":8,"url":"/task/speaker-verification/papers/3","json":"/task/speaker-verification/papers/3.json","rows":100},{"order":"archive","page":4,"of":8,"url":"/task/speaker-verification/papers/4","json":"/task/speaker-verification/papers/4.json","rows":100},{"order":"archive","page":5,"of":8,"url":"/task/speaker-verification/papers/5","json":"/task/speaker-verification/papers/5.json","rows":100},{"order":"archive","page":6,"of":8,"url":"/task/speaker-verification/papers/6","json":"/task/speaker-verification/papers/6.json","rows":100},{"order":"archive","page":7,"of":8,"url":"/task/speaker-verification/papers/7","json":"/task/speaker-verification/papers/7.json","rows":100},{"order":"archive","page":8,"of":8,"url":"/task/speaker-verification/papers/8","json":"/task/speaker-verification/papers/8.json","rows":46},{"order":"ran","page":1,"of":1,"url":"/task/speaker-verification/papers/ran/1","json":"/task/speaker-verification/papers/ran/1.json","rows":29}],"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":"edbfabed89dc869e4217112debbcf01ddc233ebf9606c964407fee42bbaf4439","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}