{"url":"/task/speaker-identification","name":"Speaker Identification","slug":"speaker-identification","description_markdown":null,"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":248,"papers_with_code":74,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":4,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/speaker-identification-on-voxceleb1","slug":"speaker-identification-on-voxceleb1","dataset":"VoxCeleb1","dataset_url":"/dataset/voxceleb1","rows_in_archive":12,"metrics":["Top-1 (%)","Top-5 (%)","Number of Params","Accuracy"],"first_row_in_archive_order":{"model":"MSM-MAE","paper_title":"Masked Modeling Duo: Towards a Universal Audio Pre-training Framework","paper_url":"/paper/masked-modeling-duo-towards-a-universal-audio","paper_date":"2024-04-09","arxiv_id":"2404.06095","code_links":[{"title":"nttcslab/m2d","url":"https://github.com/nttcslab/m2d"},{"title":"nttcslab/eval-audio-repr","url":"https://github.com/nttcslab/eval-audio-repr"}],"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":7}}},{"leaderboard":"/sota/speaker-identification-on-evi-en-gb-1","slug":"speaker-identification-on-evi-en-gb-1","dataset":"EVI en-GB","dataset_url":"/dataset/evi","rows_in_archive":1,"metrics":["Top-1 (%)"],"first_row_in_archive_order":{"model":"Fuzzy Retrieval","paper_title":"EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification","paper_url":"/paper/evi-multilingual-spoken-dialogue-tasks-and-1","paper_date":"2022-04-28","arxiv_id":"2204.13496","code_links":[{"title":"PolyAI-LDN/evi-paper","url":"https://github.com/PolyAI-LDN/evi-paper"}],"syntology":null}},{"leaderboard":"/sota/speaker-identification-on-evi-fr-fr","slug":"speaker-identification-on-evi-fr-fr","dataset":"EVI fr-FR","dataset_url":"/dataset/evi","rows_in_archive":1,"metrics":["Top-1 (%)"],"first_row_in_archive_order":{"model":"Fuzzy Retrieval","paper_title":"EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification","paper_url":"/paper/evi-multilingual-spoken-dialogue-tasks-and-1","paper_date":"2022-04-28","arxiv_id":"2204.13496","code_links":[{"title":"PolyAI-LDN/evi-paper","url":"https://github.com/PolyAI-LDN/evi-paper"}],"syntology":null}},{"leaderboard":"/sota/speaker-identification-on-evi-pl-pl","slug":"speaker-identification-on-evi-pl-pl","dataset":"EVI pl-PL","dataset_url":"/dataset/evi","rows_in_archive":1,"metrics":["Top-1 (%)"],"first_row_in_archive_order":{"model":"Fuzzy Retrieval","paper_title":"EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification","paper_url":"/paper/evi-multilingual-spoken-dialogue-tasks-and-1","paper_date":"2022-04-28","arxiv_id":"2204.13496","code_links":[{"title":"PolyAI-LDN/evi-paper","url":"https://github.com/PolyAI-LDN/evi-paper"}],"syntology":null}}],"datasets":[{"url":"/dataset/voxceleb1","name":"VoxCeleb1","full_name":"VoxCeleb1","num_papers_in_archive":680},{"url":"/dataset/csi","name":"CSI","full_name":"","num_papers_in_archive":1},{"url":"/dataset/evi","name":"EVI","full_name":"","num_papers_in_archive":1},{"url":"/dataset/fsc-p2","name":"FSC-P2","full_name":"Fearless Steps Challenge Phase2","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":74,"tagged_in_all":248,"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/speecht5-unified-modal-encoder-decoder-pre","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","date":"2021-10-14","arxiv_id":"2110.07205","repositories_listed":6,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/unispeech-sat-universal-speech-representation","title":"UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training","date":"2021-10-12","arxiv_id":"2110.05752","repositories_listed":5,"syntology":null},{"url":"/paper/masked-autoencoders-that-listen","title":"Masked Autoencoders that Listen","date":"2022-07-13","arxiv_id":"2207.06405","repositories_listed":4,"syntology":{"n":32,"n_ran":17,"n_unverified":15,"n_pointer_only":10}},{"url":"/paper/atst-audio-representation-learning-with","title":"ATST: Audio Representation Learning with Teacher-Student Transformer","date":"2022-04-26","arxiv_id":"2204.12076","repositories_listed":4,"syntology":null},{"url":"/paper/audio-albert-a-lite-bert-for-self-supervised","title":"Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation","date":"2020-05-18","arxiv_id":"2005.08575","repositories_listed":4,"syntology":null},{"url":"/paper/ssast-self-supervised-audio-spectrogram","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","date":"2021-10-19","arxiv_id":"2110.09784","repositories_listed":3,"syntology":{"n":16,"n_ran":11,"n_unverified":5,"n_pointer_only":0}},{"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/comicap-a-vlms-pipeline-for-dense-captioning","title":"ComiCap: A VLMs pipeline for dense captioning of Comic Panels","date":"2024-09-24","arxiv_id":"2409.16159","repositories_listed":2,"syntology":null},{"url":"/paper/masked-modeling-duo-towards-a-universal-audio","title":"Masked Modeling Duo: Towards a Universal Audio Pre-training Framework","date":"2024-04-09","arxiv_id":"2404.06095","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":7}},{"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/speech-resynthesis-from-discrete-disentangled","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","date":"2021-04-01","arxiv_id":"2104.00355","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/foolhd-fooling-speaker-identification-by","title":"FoolHD: Fooling speaker identification by Highly imperceptible adversarial Disturbances","date":"2020-11-17","arxiv_id":"2011.08483","repositories_listed":2,"syntology":null},{"url":"/paper/contrastive-learning-of-general-purpose-audio","title":"Contrastive Learning of General-Purpose Audio Representations","date":"2020-10-21","arxiv_id":"2010.10915","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/generative-pre-training-for-speech-with","title":"Generative Pre-Training for Speech with Autoregressive Predictive Coding","date":"2019-10-23","arxiv_id":"1910.12607","repositories_listed":2,"syntology":null},{"url":"/paper/speech-vgg-a-deep-feature-extractor-for","title":"Word-level Embeddings for Cross-Task Transfer Learning in Speech Processing","date":"2019-10-22","arxiv_id":"1910.09909","repositories_listed":2,"syntology":null},{"url":"/paper/learning-speaker-representations-with-mutual","title":"Learning Speaker Representations with Mutual Information","date":"2018-12-01","arxiv_id":"1812.00271","repositories_listed":2,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"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/whisper-speaker-identification-leveraging-pre","title":"Whisper Speaker Identification: Leveraging Pre-Trained Multilingual Transformers for Robust Speaker Embeddings","date":"2025-03-13","arxiv_id":"2503.10446","repositories_listed":1,"syntology":null},{"url":"/paper/friends-mmc-a-dataset-for-multi-modal-multi","title":"Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding","date":"2024-12-23","arxiv_id":"2412.17295","repositories_listed":1,"syntology":null},{"url":"/paper/towards-speaker-identification-with-minimal","title":"Towards Speaker Identification with Minimal Dataset and Constrained Resources using 1D-Convolution Neural Network","date":"2024-11-22","arxiv_id":"2411.15082","repositories_listed":1,"syntology":null},{"url":"/paper/disentangling-textual-and-acoustic-features","title":"Disentangling Textual and Acoustic Features of Neural Speech Representations","date":"2024-10-03","arxiv_id":"2410.03037","repositories_listed":1,"syntology":null},{"url":"/paper/just-asr-llm-a-study-on-speech-large-language","title":"Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken Dialogue","date":"2024-09-07","arxiv_id":"2409.04927","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-for-speaker-identification","title":"Deep Learning for Speaker Identification: Architectural Insights from AB-1 Corpus Analysis and Performance Evaluation","date":"2024-08-13","arxiv_id":"2408.06804","repositories_listed":1,"syntology":null},{"url":"/paper/identifying-speakers-in-dialogue-transcripts","title":"Identifying Speakers in Dialogue Transcripts: A Text-based Approach Using Pretrained Language Models","date":"2024-07-16","arxiv_id":"2407.12094","repositories_listed":1,"syntology":null},{"url":"/paper/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/comix-a-comprehensive-benchmark-for-multi","title":"CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding","date":"2024-07-04","arxiv_id":"2407.03550","repositories_listed":1,"syntology":null}],"syntology_records":8,"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"}}