{"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_unverified":6,"n_pointer_only":2}}}],"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":102,"tagged_in_all":435,"items":[{"url":"/paper/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":6,"n_unverified":3,"n_pointer_only":6}},{"url":"/paper/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_unverified":2,"n_pointer_only":5}},{"url":"/paper/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":3,"n_unverified":20,"n_pointer_only":1}},{"url":"/paper/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":5,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/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":3,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/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","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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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","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","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","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","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","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","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_unverified":6,"n_pointer_only":2}},{"url":"/paper/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","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","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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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","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","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","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","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","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","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":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/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","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","title":"VoxCeleb2: Deep Speaker Recognition","date":"2018-06-14","arxiv_id":"1806.05622","repositories_listed":2,"syntology":{"n":13,"n_ran":0,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/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","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","title":"Private kNN-VC: Interpretable Anonymization of Converted Speech","date":"2025-05-23","arxiv_id":"2505.17584","repositories_listed":1,"syntology":null}],"syntology_records":10,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}