{"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-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_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":7,"phrase":"7 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/masked-modeling-duo-towards-a-universal-audio#ran","syntology_url":"https://syntology.ai/paper/2404.06095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06095"}},"official":{"repos":["nttcslab/m2d","nttcslab/eval-audio-repr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"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 (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":3,"rows_per_page":100,"shown":100,"of":248,"of_with_code":74,"tagged_in_all":248,"counts":{"archive_papers_tagged":248,"with_a_code_link":74,"where_syntology_ran_a_sample":15,"not_listed_spam_title":0,"listed":248,"listed_where_code_ran":15,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":4,"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/speecht5-unified-modal-encoder-decoder-pre","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/speecht5-unified-modal-encoder-decoder-pre#ran","syntology_url":"https://syntology.ai/paper/2110.07205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.07205"}},"official":{"repos":["microsoft/speecht5"],"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/unispeech-sat-universal-speech-representation","slug":"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","slug":"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_constructed":12,"n_ran_checked":16,"n_instrument":1,"n_unverified":15,"n_honours":1,"n_violates":1,"n_no_contract":14,"n_pointer_only":10,"phrase":"17 ran (of which 12 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/masked-autoencoders-that-listen#ran","syntology_url":"https://syntology.ai/paper/2207.06405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06405"}},"official":{"repos":["facebookresearch/audiomae"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/atst-audio-representation-learning-with","slug":"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","slug":"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","slug":"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":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/ssast-self-supervised-audio-spectrogram#ran","syntology_url":"https://syntology.ai/paper/2110.09784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.09784"}},"official":{"repos":["YuanGongND/ssast"],"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/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/comicap-a-vlms-pipeline-for-dense-captioning","slug":"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","slug":"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_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":7,"phrase":"7 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/masked-modeling-duo-towards-a-universal-audio#ran","syntology_url":"https://syntology.ai/paper/2404.06095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06095"}},"official":{"repos":["nttcslab/m2d","nttcslab/eval-audio-repr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/speech-resynthesis-from-discrete-disentangled","slug":"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_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/speech-resynthesis-from-discrete-disentangled#ran","syntology_url":"https://syntology.ai/paper/2104.00355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00355"}},"official":{"repos":["facebookresearch/speech-resynthesis"],"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/foolhd-fooling-speaker-identification-by","slug":"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","slug":"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","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/generative-pre-training-for-speech-with","slug":"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","slug":"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","slug":"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":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-speaker-representations-with-mutual#ran","syntology_url":"https://syntology.ai/paper/1812.00271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.00271"}},"official":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/whisper-speaker-identification-leveraging-pre","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","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/comix-a-comprehensive-benchmark-for-multi","slug":"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},{"url":"/paper/ssamba-self-supervised-audio-representation","slug":"ssamba-self-supervised-audio-representation","title":"SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model","date":"2024-05-20","arxiv_id":"2405.11831","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/ssamba-self-supervised-audio-representation#ran","syntology_url":"https://syntology.ai/paper/2405.11831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11831"}},"official":{"repos":["siavashshams/ssamba"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/sig-speaker-identification-in-literature-via","slug":"sig-speaker-identification-in-literature-via","title":"SIG: Speaker Identification in Literature via Prompt-Based Generation","date":"2023-12-22","arxiv_id":"2312.14590","repositories_listed":1,"syntology":null},{"url":"/paper/instructerc-reforming-emotion-recognition-in","slug":"instructerc-reforming-emotion-recognition-in","title":"InstructERC: Reforming Emotion Recognition in Conversation with Multi-task Retrieval-Augmented Large Language Models","date":"2023-09-21","arxiv_id":"2309.11911","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/instructerc-reforming-emotion-recognition-in#ran","syntology_url":"https://syntology.ai/paper/2309.11911","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.11911"}},"official":{"repos":["LIN-SHANG/InstructERC"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/an-effective-transformer-based-contextual","slug":"an-effective-transformer-based-contextual","title":"An Effective Transformer-based Contextual Model and Temporal Gate Pooling for Speaker Identification","date":"2023-08-22","arxiv_id":"2308.11241","repositories_listed":1,"syntology":null},{"url":"/paper/gammatonegram-representation-for-end-to-end","slug":"gammatonegram-representation-for-end-to-end","title":"Gammatonegram Representation for End-to-End Dysarthric Speech Processing Tasks: Speech Recognition, Speaker Identification, and Intelligibility Assessment","date":"2023-07-06","arxiv_id":"2307.03296","repositories_listed":1,"syntology":null},{"url":"/paper/non-uniform-speaker-disentanglement-for","slug":"non-uniform-speaker-disentanglement-for","title":"Non-uniform Speaker Disentanglement For Depression Detection From Raw Speech Signals","date":"2023-06-02","arxiv_id":"2306.01861","repositories_listed":1,"syntology":null},{"url":"/paper/mpchat-towards-multimodal-persona-grounded","slug":"mpchat-towards-multimodal-persona-grounded","title":"MPCHAT: Towards Multimodal Persona-Grounded Conversation","date":"2023-05-27","arxiv_id":"2305.17388","repositories_listed":1,"syntology":null},{"url":"/paper/gift-graph-induced-fine-tuning-for-multi","slug":"gift-graph-induced-fine-tuning-for-multi","title":"GIFT: Graph-Induced Fine-Tuning for Multi-Party Conversation Understanding","date":"2023-05-16","arxiv_id":"2305.09360","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-speech-representation-pooling","slug":"unsupervised-speech-representation-pooling","title":"Unsupervised Speech Representation Pooling Using Vector Quantization","date":"2023-04-08","arxiv_id":"2304.03940","repositories_listed":1,"syntology":null},{"url":"/paper/asit-audio-spectrogram-vision-transformer-for","slug":"asit-audio-spectrogram-vision-transformer-for","title":"ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification","date":"2022-11-23","arxiv_id":"2211.13189","repositories_listed":1,"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/asit-audio-spectrogram-vision-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2211.13189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13189"}},"official":{"repos":["sara-ahmed/asit"],"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/melhubert-a-simplified-hubert-on-mel","slug":"melhubert-a-simplified-hubert-on-mel","title":"MelHuBERT: A simplified HuBERT on Mel spectrograms","date":"2022-11-17","arxiv_id":"2211.09944","repositories_listed":1,"syntology":null},{"url":"/paper/masked-modeling-duo-learning-representations","slug":"masked-modeling-duo-learning-representations","title":"Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input","date":"2022-10-26","arxiv_id":"2210.14648","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/masked-modeling-duo-learning-representations#ran","syntology_url":"https://syntology.ai/paper/2210.14648","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.14648"}},"official":{"repos":["nttcslab/m2d"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-lingual-speaker-identification-using","slug":"cross-lingual-speaker-identification-using","title":"Cross-Lingual Speaker Identification Using Distant Supervision","date":"2022-10-11","arxiv_id":"2210.05780","repositories_listed":1,"syntology":null},{"url":"/paper/indicsuperb-a-speech-processing-universal","slug":"indicsuperb-a-speech-processing-universal","title":"IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages","date":"2022-08-24","arxiv_id":"2208.11761","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/indicsuperb-a-speech-processing-universal#ran","syntology_url":"https://syntology.ai/paper/2208.11761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.11761"}},"official":{"repos":["AI4Bharat/indicSUPERB"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/end-to-end-chinese-speaker-identification","slug":"end-to-end-chinese-speaker-identification","title":"End-to-End Chinese Speaker Identification","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/extended-u-net-for-speaker-verification-in","slug":"extended-u-net-for-speaker-verification-in","title":"Extended U-Net for Speaker Verification in Noisy Environments","date":"2022-06-27","arxiv_id":"2206.13044","repositories_listed":1,"syntology":null},{"url":"/paper/evi-multilingual-spoken-dialogue-tasks-and-1","slug":"evi-multilingual-spoken-dialogue-tasks-and-1","title":"EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification","date":"2022-04-28","arxiv_id":"2204.13496","repositories_listed":1,"syntology":null},{"url":"/paper/streaming-speaker-attributed-asr-with-token","slug":"streaming-speaker-attributed-asr-with-token","title":"Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings","date":"2022-03-30","arxiv_id":"2203.16685","repositories_listed":1,"syntology":null},{"url":"/paper/slue-new-benchmark-tasks-for-spoken-language","slug":"slue-new-benchmark-tasks-for-spoken-language","title":"SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech","date":"2021-11-19","arxiv_id":"2111.10367","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/slue-new-benchmark-tasks-for-spoken-language#ran","syntology_url":"https://syntology.ai/paper/2111.10367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.10367"}},"official":{"repos":["asappresearch/slue-toolkit"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/pl-eesr-perceptual-loss-based-end-to-end","slug":"pl-eesr-perceptual-loss-based-end-to-end","title":"PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction","date":"2021-10-03","arxiv_id":"2110.00940","repositories_listed":1,"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/pl-eesr-perceptual-loss-based-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2110.00940","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.00940"}},"official":{"repos":["mmmmayi/pl-eesr"],"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":["official"]}}},{"url":"/paper/compositional-affinity-propagation-when","slug":"compositional-affinity-propagation-when","title":"Compositional Clustering: Applications to Multi-Label Object Recognition and Speaker Identification","date":"2021-09-09","arxiv_id":"2109.04160","repositories_listed":1,"syntology":null},{"url":"/paper/fastaudio-a-learnable-audio-front-end-for","slug":"fastaudio-a-learnable-audio-front-end-for","title":"FastAudio: A Learnable Audio Front-End for Spoof Speech Detection","date":"2021-09-06","arxiv_id":"2109.02774","repositories_listed":1,"syntology":null},{"url":"/paper/towards-making-the-most-of-dialogue","slug":"towards-making-the-most-of-dialogue","title":"Towards Making the Most of Dialogue Characteristics for Neural Chat Translation","date":"2021-09-02","arxiv_id":"2109.00668","repositories_listed":1,"syntology":null},{"url":"/paper/learning-audio-visual-dereverberation","slug":"learning-audio-visual-dereverberation","title":"Learning Audio-Visual Dereverberation","date":"2021-06-14","arxiv_id":"2106.07732","repositories_listed":1,"syntology":null},{"url":"/paper/mpc-bert-a-pre-trained-language-model-for","slug":"mpc-bert-a-pre-trained-language-model-for","title":"MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding","date":"2021-06-03","arxiv_id":"2106.01541","repositories_listed":1,"syntology":null},{"url":"/paper/supervised-speech-representation-learning-for","slug":"supervised-speech-representation-learning-for","title":"Supervised Speech Representation Learning for Parkinson's Disease Classification","date":"2021-06-01","arxiv_id":"2106.00531","repositories_listed":1,"syntology":null},{"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/blind-speech-separation-and-dereverberation","slug":"blind-speech-separation-and-dereverberation","title":"Blind Speech Separation and Dereverberation using Neural Beamforming","date":"2021-03-24","arxiv_id":"2103.13443","repositories_listed":1,"syntology":null},{"url":"/paper/a-modulation-domain-loss-for-neural-network-1","slug":"a-modulation-domain-loss-for-neural-network-1","title":"A Modulation-Domain Loss for Neural-Network-based Real-time Speech Enhancement","date":"2021-02-15","arxiv_id":"2102.07330","repositories_listed":1,"syntology":null},{"url":"/paper/attention-based-multi-task-learning-for","slug":"attention-based-multi-task-learning-for","title":"Attention-based multi-task learning for speech-enhancement and speaker-identification in multi-speaker dialogue scenario","date":"2021-01-07","arxiv_id":"2101.02550","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/minimum-bayes-risk-training-for-end-to-end","slug":"minimum-bayes-risk-training-for-end-to-end","title":"Minimum Bayes Risk Training for End-to-End Speaker-Attributed ASR","date":"2020-11-03","arxiv_id":"2011.02921","repositories_listed":1,"syntology":null},{"url":"/paper/compositional-embedding-models-for-speaker","slug":"compositional-embedding-models-for-speaker","title":"Compositional embedding models for speaker identification and diarization with simultaneous speech from 2+ speakers","date":"2020-10-22","arxiv_id":"2010.11803","repositories_listed":1,"syntology":null},{"url":"/paper/sum-product-networks-for-robust-automatic","slug":"sum-product-networks-for-robust-automatic","title":"Sum-Product Networks for Robust Automatic Speaker Identification","date":"2020-08-13","arxiv_id":"1910.11969","repositories_listed":1,"syntology":null},{"url":"/paper/investigation-of-end-to-end-speaker","slug":"investigation-of-end-to-end-speaker","title":"Investigation of End-To-End Speaker-Attributed ASR for Continuous Multi-Talker Recordings","date":"2020-08-11","arxiv_id":"2008.04546","repositories_listed":1,"syntology":null},{"url":"/paper/audino-a-modern-annotation-tool-for-audio-and","slug":"audino-a-modern-annotation-tool-for-audio-and","title":"audino: A Modern Annotation Tool for Audio and Speech","date":"2020-06-09","arxiv_id":"2006.05236","repositories_listed":1,"syntology":null},{"url":"/paper/identify-speakers-in-cocktail-parties-with","slug":"identify-speakers-in-cocktail-parties-with","title":"Identify Speakers in Cocktail Parties with End-to-End Attention","date":"2020-05-22","arxiv_id":"2005.11408","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/improving-speaker-discrimination-of-target","slug":"improving-speaker-discrimination-of-target","title":"Improving speaker discrimination of target speech extraction with time-domain SpeakerBeam","date":"2020-01-23","arxiv_id":"2001.08378","repositories_listed":1,"syntology":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/on-learning-associations-of-faces-and-voices","slug":"on-learning-associations-of-faces-and-voices","title":"On Learning Associations of Faces and Voices","date":"2018-05-15","arxiv_id":"1805.05553","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/on-learning-associations-of-faces-and-voices#ran","syntology_url":"https://syntology.ai/paper/1805.05553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.05553"}},"official":null}},{"url":"/paper/a-domain-agnostic-approach-for-opinion","slug":"a-domain-agnostic-approach-for-opinion","title":"A domain-agnostic approach for opinion prediction on speech","date":"2016-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-generative-product-of-filters-model-of","slug":"a-generative-product-of-filters-model-of","title":"A Generative Product-of-Filters Model of Audio","date":"2013-12-20","arxiv_id":"1312.5857","repositories_listed":1,"syntology":null},{"url":null,"slug":"rhythm-features-for-speaker-identification","title":"Rhythm Features for Speaker Identification","date":"2025-06-07","arxiv_id":"2506.06834","repositories_listed":0,"syntology":null},{"url":null,"slug":"french-listening-tests-for-the-assessment-of","title":"French Listening Tests for the Assessment of Intelligibility, Quality, and Identity of Body-Conducted Speech Enhancement","date":"2025-06-04","arxiv_id":"2506.04495","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-unlearning","title":"Speech Unlearning","date":"2025-06-01","arxiv_id":"2506.00848","repositories_listed":0,"syntology":null},{"url":null,"slug":"pretraining-multi-speaker-identification-for","title":"Pretraining Multi-Speaker Identification for Neural Speaker Diarization","date":"2025-05-30","arxiv_id":"2505.24545","repositories_listed":0,"syntology":null},{"url":null,"slug":"rewind-speech-time-reversal-for-enhancing","title":"REWIND: Speech Time Reversal for Enhancing Speaker Representations in Diffusion-based Voice Conversion","date":"2025-05-27","arxiv_id":"2505.20756","repositories_listed":0,"syntology":null},{"url":null,"slug":"hpp-voice-a-large-scale-evaluation-of-speech","title":"HPP-Voice: A Large-Scale Evaluation of Speech Embeddings for Multi-Phenotypic Classification","date":"2025-05-22","arxiv_id":"2505.16490","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantized-approximate-signal-processing-qasp","title":"Quantized Approximate Signal Processing (QASP): Towards Homomorphic Encryption for audio","date":"2025-05-15","arxiv_id":"2505.10500","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-dialect-gaps-to-identity-maps-tackling","title":"From Dialect Gaps to Identity Maps: Tackling Variability in Speaker Verification","date":"2025-04-21","arxiv_id":"2505.04629","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-fuzzy-fingerprints-benchmarking-text","title":"Speaker Fuzzy Fingerprints: Benchmarking Text-Based Identification in Multiparty Dialogues","date":"2025-04-21","arxiv_id":"2504.14963","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-ft-merging-pre-trained-and-fine-tuned","title":"Speech-FT: Merging Pre-trained And Fine-Tuned Speech Representation Models For Cross-Task Generalization","date":"2025-02-18","arxiv_id":"2502.12672","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-preliminary-exploration-with-gpt-4o-voice","title":"A Preliminary Exploration with GPT-4o Voice Mode","date":"2025-02-14","arxiv_id":"2502.09940","repositories_listed":0,"syntology":null},{"url":null,"slug":"scdiar-a-streaming-diarization-system-based","title":"SCDiar: a streaming diarization system based on speaker change detection and speech recognition","date":"2025-01-28","arxiv_id":"2501.16641","repositories_listed":0,"syntology":null},{"url":null,"slug":"characteristic-specific-partial-fine-tuning","title":"Characteristic-Specific Partial Fine-Tuning for Efficient Emotion and Speaker Adaptation in Codec Language Text-to-Speech Models","date":"2025-01-24","arxiv_id":"2501.14273","repositories_listed":0,"syntology":null},{"url":null,"slug":"polinterviews-a-dataset-of-german-politician","title":"PolInterviews -- A Dataset of German Politician Public Broadcast Interviews","date":"2025-01-08","arxiv_id":"2501.04484","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-unlearning-reveals-that-the-gender","title":"Machine Unlearning reveals that the Gender-based Violence Victim Condition can be detected from Speech in a Speaker-Agnostic Setting","date":"2024-11-27","arxiv_id":"2411.18177","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-advanced-speech-signal-processing-a","title":"Towards Advanced Speech Signal Processing: A Statistical Perspective on Convolution-Based Architectures and its Applications","date":"2024-11-20","arxiv_id":"2411.18636","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-talker-identity-aids-with","title":"Incorporating Talker Identity Aids With Improving Speech Recognition in Adversarial Environments","date":"2024-10-07","arxiv_id":"2410.05423","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-open-set-speaker-identification","title":"Enhancing Open-Set Speaker Identification through Rapid Tuning with Speaker Reciprocal Points and Negative Sample","date":"2024-09-24","arxiv_id":"2409.15742","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-vq-vae-with-prosody-parameters-for","title":"Exploring VQ-VAE with Prosody Parameters for Speaker Anonymization","date":"2024-09-24","arxiv_id":"2409.15882","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-redundant-is-the-transformer-stack-in","title":"How Redundant Is the Transformer Stack in Speech Representation Models?","date":"2024-09-10","arxiv_id":"2409.16302","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-toolkit-for-joint-speaker-diarization-and","title":"A Toolkit for Joint Speaker Diarization and Identification with Application to Speaker-Attributed ASR","date":"2024-09-09","arxiv_id":"2409.05750","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-residual-extraction-based-pre","title":"Progressive Residual Extraction based Pre-training for Speech Representation Learning","date":"2024-08-31","arxiv_id":"2409.00387","repositories_listed":0,"syntology":null},{"url":null,"slug":"dasb-discrete-audio-and-speech-benchmark","title":"DASB -- Discrete Audio and Speech Benchmark","date":"2024-06-20","arxiv_id":"2406.14294","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-speaker-identity-coding-in-self","title":"Evaluating Speaker Identity Coding in Self-supervised Models and Humans","date":"2024-06-14","arxiv_id":"2406.10401","repositories_listed":0,"syntology":null},{"url":null,"slug":"timit-speaker-profiling-a-comparison-of-multi","title":"TIMIT Speaker Profiling: A Comparison of Multi-task learning and Single-task learning Approaches","date":"2024-04-18","arxiv_id":"2404.12077","repositories_listed":0,"syntology":null},{"url":null,"slug":"removing-speaker-information-from-speech","title":"Removing Speaker Information from Speech Representation using Variable-Length Soft Pooling","date":"2024-04-01","arxiv_id":"2404.00856","repositories_listed":0,"syntology":null}],"syntology_records":16,"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-identification-on-voxceleb1","since_archive":"/sota/speaker-identification-on-voxceleb1#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":15,"papers_where_code_ran_first_page":"/task/speaker-identification/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":3,"url":"/task/speaker-identification/papers/2","json":"/task/speaker-identification/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/speaker-identification/papers/3","json":"/task/speaker-identification/papers/3.json","rows":48},{"order":"ran","page":1,"of":1,"url":"/task/speaker-identification/papers/ran/1","json":"/task/speaker-identification/papers/ran/1.json","rows":15}],"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":"f0e1f4b69e29351ab98ed7b3753eb37ec7f1cb096154adedf595e334f2b2889e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}