{"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-diarization","name":"Speaker Diarization","slug":"speaker-diarization","description_markdown":"**Speaker Diarization** is the task of segmenting and co-indexing audio recordings by speaker. The way the task is commonly defined, the goal is not to identify known speakers, but to co-index segments that are attributed to the same speaker; in other words, diarization implies finding speaker boundaries and grouping segments that belong to the same speaker, and, as a by-product, determining the number of distinct speakers. In combination with speech recognition, diarization enables speaker-attributed speech-to-text transcription.\n\n\n<span class=\"description-source\">Source: [Improving Diarization Robustness using Diversification, Randomization and the DOVER Algorithm ](https://arxiv.org/abs/1910.11691)</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":328,"papers_with_code":93,"benchmarks":12,"benchmark_tables_in_archive":15,"benchmark_tables_shown":15,"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":11,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/speaker-diarization-on-callhome","slug":"speaker-diarization-on-callhome","dataset":"CALLHOME","dataset_url":"/dataset/callhome-american-english-speech","rows_in_archive":10,"metrics":["DER(%)","DER(ig olp)","FA","MI","CF"],"first_row_in_archive_order":{"model":"TOLD","paper_title":"TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization","paper_url":"/paper/told-a-novel-two-stage-overlap-aware","paper_date":"2023-03-08","arxiv_id":"2303.05397","code_links":[{"title":"alibaba-damo-academy/FunASR","url":"https://github.com/alibaba-damo-academy/FunASR"}],"syntology":null}},{"leaderboard":"/sota/speaker-diarization-on-nist-sre-2000","slug":"speaker-diarization-on-nist-sre-2000","dataset":"NIST-SRE 2000","dataset_url":null,"rows_in_archive":5,"metrics":["DER(%)"],"first_row_in_archive_order":{"model":"x-vector (MCGAN)","paper_title":"TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context","paper_url":"/paper/titanet-neural-model-for-speaker","paper_date":"2021-10-08","arxiv_id":"2110.04410","code_links":[{"title":"NVIDIA/NeMo","url":"https://github.com/NVIDIA/NeMo"},{"title":"Wadaboa/titanet","url":"https://github.com/Wadaboa/titanet"}],"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"]}}}},{"leaderboard":"/sota/speaker-diarization-on-ami-lapel","slug":"speaker-diarization-on-ami-lapel","dataset":"AMI Lapel","dataset_url":null,"rows_in_archive":4,"metrics":["DER(%)"],"first_row_in_archive_order":{"model":"TitaNet-M (NME-SC)","paper_title":"TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context","paper_url":"/paper/titanet-neural-model-for-speaker","paper_date":"2021-10-08","arxiv_id":"2110.04410","code_links":[{"title":"NVIDIA/NeMo","url":"https://github.com/NVIDIA/NeMo"},{"title":"Wadaboa/titanet","url":"https://github.com/Wadaboa/titanet"}],"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"]}}}},{"leaderboard":"/sota/speaker-diarization-on-ami-mixheadset","slug":"speaker-diarization-on-ami-mixheadset","dataset":"AMI MixHeadset","dataset_url":null,"rows_in_archive":4,"metrics":["DER(%)"],"first_row_in_archive_order":{"model":"TitaNet-L (NME-SC)","paper_title":"TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context","paper_url":"/paper/titanet-neural-model-for-speaker","paper_date":"2021-10-08","arxiv_id":"2110.04410","code_links":[{"title":"NVIDIA/NeMo","url":"https://github.com/NVIDIA/NeMo"},{"title":"Wadaboa/titanet","url":"https://github.com/Wadaboa/titanet"}],"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"]}}}},{"leaderboard":"/sota/speaker-diarization-on-ch109","slug":"speaker-diarization-on-ch109","dataset":"CH109","dataset_url":null,"rows_in_archive":4,"metrics":["DER(%)"],"first_row_in_archive_order":{"model":"TitaNet-S (NME-SC)","paper_title":"TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context","paper_url":"/paper/titanet-neural-model-for-speaker","paper_date":"2021-10-08","arxiv_id":"2110.04410","code_links":[{"title":"NVIDIA/NeMo","url":"https://github.com/NVIDIA/NeMo"},{"title":"Wadaboa/titanet","url":"https://github.com/Wadaboa/titanet"}],"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"]}}}},{"leaderboard":"/sota/speaker-diarization-on-dihard-1","slug":"speaker-diarization-on-dihard-1","dataset":"DIHARD","dataset_url":null,"rows_in_archive":3,"metrics":["DER(%)","FA","Miss"],"first_row_in_archive_order":{"model":"pyannote (waveform)","paper_title":"pyannote.audio: neural building blocks for speaker diarization","paper_url":"/paper/pyannoteaudio-neural-building-blocks-for","paper_date":"2019-11-04","arxiv_id":"1911.01255","code_links":[{"title":"pyannote/pyannote-audio","url":"https://github.com/pyannote/pyannote-audio"},{"title":"muskang48/Speaker-Diarization","url":"https://github.com/muskang48/Speaker-Diarization"},{"title":"MarvinLvn/voice-type-classifier","url":"https://github.com/MarvinLvn/voice-type-classifier"}],"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":0,"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/pyannoteaudio-neural-building-blocks-for#ran","syntology_url":"https://syntology.ai/paper/1911.01255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.01255"}},"official":{"repos":["pyannote/pyannote-audio"],"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"]}}}},{"leaderboard":"/sota/speaker-diarization-on-etape","slug":"speaker-diarization-on-etape","dataset":"ETAPE","dataset_url":null,"rows_in_archive":3,"metrics":["DER(%)","FA","Miss"],"first_row_in_archive_order":{"model":"pyannote (waveform)","paper_title":"pyannote.audio: neural building blocks for speaker diarization","paper_url":"/paper/pyannoteaudio-neural-building-blocks-for","paper_date":"2019-11-04","arxiv_id":"1911.01255","code_links":[{"title":"pyannote/pyannote-audio","url":"https://github.com/pyannote/pyannote-audio"},{"title":"muskang48/Speaker-Diarization","url":"https://github.com/muskang48/Speaker-Diarization"},{"title":"MarvinLvn/voice-type-classifier","url":"https://github.com/MarvinLvn/voice-type-classifier"}],"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":0,"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/pyannoteaudio-neural-building-blocks-for#ran","syntology_url":"https://syntology.ai/paper/1911.01255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.01255"}},"official":{"repos":["pyannote/pyannote-audio"],"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"]}}}},{"leaderboard":"/sota/speaker-diarization-on-ami","slug":"speaker-diarization-on-ami","dataset":"AMI","dataset_url":null,"rows_in_archive":2,"metrics":["DER(%)","FA","Miss"],"first_row_in_archive_order":{"model":"pyannote (waveform)","paper_title":"pyannote.audio: neural building blocks for speaker diarization","paper_url":"/paper/pyannoteaudio-neural-building-blocks-for","paper_date":"2019-11-04","arxiv_id":"1911.01255","code_links":[{"title":"pyannote/pyannote-audio","url":"https://github.com/pyannote/pyannote-audio"},{"title":"muskang48/Speaker-Diarization","url":"https://github.com/muskang48/Speaker-Diarization"},{"title":"MarvinLvn/voice-type-classifier","url":"https://github.com/MarvinLvn/voice-type-classifier"}],"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":0,"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/pyannoteaudio-neural-building-blocks-for#ran","syntology_url":"https://syntology.ai/paper/1911.01255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.01255"}},"official":{"repos":["pyannote/pyannote-audio"],"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"]}}}},{"leaderboard":"/sota/speaker-diarization-on-callhome-109","slug":"speaker-diarization-on-callhome-109","dataset":"CALLHOME-109","dataset_url":"/dataset/callhome-american-english-speech","rows_in_archive":2,"metrics":["DER(%)"],"first_row_in_archive_order":{"model":"titanet-s","paper_title":"TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context","paper_url":"/paper/titanet-neural-model-for-speaker","paper_date":"2021-10-08","arxiv_id":"2110.04410","code_links":[{"title":"NVIDIA/NeMo","url":"https://github.com/NVIDIA/NeMo"},{"title":"Wadaboa/titanet","url":"https://github.com/Wadaboa/titanet"}],"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"]}}}},{"leaderboard":"/sota/speaker-diarization-on-alimeeting","slug":"speaker-diarization-on-alimeeting","dataset":"AliMeeting","dataset_url":"/dataset/alimeeting","rows_in_archive":1,"metrics":["DER(%)"],"first_row_in_archive_order":{"model":"SOND","paper_title":"Speaker Embedding-aware Neural Diarization: an Efficient Framework for Overlapping Speech Diarization in Meeting Scenarios","paper_url":"/paper/speaker-embedding-aware-neural-diarization-a","paper_date":"2022-03-18","arxiv_id":"2203.09767","code_links":[{"title":"alibaba-damo-academy/FunASR","url":"https://github.com/alibaba-damo-academy/FunASR"}],"syntology":null}},{"leaderboard":"/sota/speaker-diarization-on-dihard-ii","slug":"speaker-diarization-on-dihard-ii","dataset":"DIHARD II","dataset_url":"/dataset/dihard-ii","rows_in_archive":1,"metrics":["DER(%)","DER - no overlap"],"first_row_in_archive_order":{"model":"UIS-RNN-SML","paper_title":"Supervised online diarization with sample mean loss for multi-domain data","paper_url":"/paper/supervised-online-diarization-with-sample","paper_date":"2019-11-04","arxiv_id":"1911.01266","code_links":[{"title":"DonkeyShot21/uis-rnn-sml","url":"https://github.com/DonkeyShot21/uis-rnn-sml"}],"syntology":null}},{"leaderboard":"/sota/speaker-diarization-on-hub5-00-callhome","slug":"speaker-diarization-on-hub5-00-callhome","dataset":"Hub5'00 CallHome","dataset_url":"/dataset/callhome-american-english-speech","rows_in_archive":1,"metrics":["V"],"first_row_in_archive_order":{"model":"UIS-RNN","paper_title":"Fully Supervised Speaker Diarization","paper_url":"/paper/fully-supervised-speaker-diarization","paper_date":"2018-10-10","arxiv_id":"1810.04719","code_links":[{"title":"google/uis-rnn","url":"https://github.com/google/uis-rnn"}],"syntology":null}},{"leaderboard":null,"slug":"speaker-diarization-on-call-home-american","dataset":"call_home_american_english_speech","dataset_url":null,"rows_in_archive":0,"metrics":["Test DER"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"speaker-diarization-on-callhome-nist-sre-2000","dataset":"CALLHOME (NIST-SRE-2000 Disc8)","dataset_url":null,"rows_in_archive":0,"metrics":["Test DER"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"speaker-diarization-on-dihard3-eval","dataset":"DIHARD3-eval","dataset_url":null,"rows_in_archive":0,"metrics":["Test DER"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/ava","name":"AVA","full_name":"Atomic Visual Actions","num_papers_in_archive":113},{"url":"/dataset/alimeeting","name":"AliMeeting","full_name":"Multi-Channel Multi-Party Meeting Transcription Challenge","num_papers_in_archive":46},{"url":"/dataset/chime-5","name":"CHiME-5","full_name":"CHiME Speech Separation and Recognition Challenge","num_papers_in_archive":42},{"url":"/dataset/dihard-ii","name":"DIHARD II","full_name":"","num_papers_in_archive":34},{"url":"/dataset/ava-activespeaker","name":"AVA-ActiveSpeaker","full_name":"","num_papers_in_archive":22},{"url":"/dataset/magicdata-ramc","name":"MagicData-RAMC","full_name":"","num_papers_in_archive":12},{"url":"/dataset/callhome-american-english-speech","name":"CALLHOME American English Speech","full_name":"","num_papers_in_archive":11},{"url":"/dataset/ava-speech","name":"AVA-Speech","full_name":"","num_papers_in_archive":10},{"url":"/dataset/asr-ramc-bigccsc-a-chinese-conversational","name":"ASR-RAMC-BIGCCSC: A CHINESE CONVERSATIONAL SPEECH CORPUS","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},{"url":"/dataset/radiotalk","name":"RadioTalk","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":4,"rows_per_page":100,"shown":100,"of":328,"of_with_code":93,"tagged_in_all":328,"counts":{"archive_papers_tagged":328,"with_a_code_link":93,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":328,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/ava-avd-audio-visual-speaker-diarization-in","slug":"ava-avd-audio-visual-speaker-diarization-in","title":"AVA-AVD: Audio-Visual Speaker Diarization in the Wild","date":"2021-11-29","arxiv_id":"2111.14448","repositories_listed":9,"syntology":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/speech-emotion-diarization-which-emotion","slug":"speech-emotion-diarization-which-emotion","title":"Speech Emotion Diarization: Which Emotion Appears When?","date":"2023-06-22","arxiv_id":"2306.12991","repositories_listed":3,"syntology":null},{"url":"/paper/the-third-dihard-diarization-challenge","slug":"the-third-dihard-diarization-challenge","title":"The Third DIHARD Diarization Challenge","date":"2020-12-02","arxiv_id":"2012.01477","repositories_listed":3,"syntology":null},{"url":"/paper/end-to-end-speaker-diarization-for-an-unknown","slug":"end-to-end-speaker-diarization-for-an-unknown","title":"End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors","date":"2020-05-20","arxiv_id":"2005.09921","repositories_listed":3,"syntology":{"n":21,"n_ran":19,"n_constructed":0,"n_ran_checked":19,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/end-to-end-speaker-diarization-for-an-unknown#ran","syntology_url":"https://syntology.ai/paper/2005.09921","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.09921"}},"official":{"repos":["hitachi-speech/EEND"],"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/speech-recognition-and-multi-speaker","slug":"speech-recognition-and-multi-speaker","title":"Speech Recognition and Multi-Speaker Diarization of Long Conversations","date":"2020-05-16","arxiv_id":"2005.08072","repositories_listed":3,"syntology":null},{"url":"/paper/pyannoteaudio-neural-building-blocks-for","slug":"pyannoteaudio-neural-building-blocks-for","title":"pyannote.audio: neural building blocks for speaker diarization","date":"2019-11-04","arxiv_id":"1911.01255","repositories_listed":3,"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":0,"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/pyannoteaudio-neural-building-blocks-for#ran","syntology_url":"https://syntology.ai/paper/1911.01255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.01255"}},"official":{"repos":["pyannote/pyannote-audio"],"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/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/diarizationlm-speaker-diarization-post","slug":"diarizationlm-speaker-diarization-post","title":"DiarizationLM: Speaker Diarization Post-Processing with Large Language Models","date":"2024-01-07","arxiv_id":"2401.03506","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/diarizationlm-speaker-diarization-post#ran","syntology_url":"https://syntology.ai/paper/2401.03506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03506"}},"official":{"repos":["google/speaker-id"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-audio-teacher-student","slug":"self-supervised-audio-teacher-student","title":"Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks","date":"2023-06-07","arxiv_id":"2306.04186","repositories_listed":2,"syntology":null},{"url":"/paper/ber-balanced-error-rate-for-speaker","slug":"ber-balanced-error-rate-for-speaker","title":"BER: Balanced Error Rate For Speaker Diarization","date":"2022-11-08","arxiv_id":"2211.04304","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/from-simulated-mixtures-to-simulated","slug":"from-simulated-mixtures-to-simulated","title":"From Simulated Mixtures to Simulated Conversations as Training Data for End-to-End Neural Diarization","date":"2022-04-02","arxiv_id":"2204.00890","repositories_listed":2,"syntology":null},{"url":"/paper/speaker-embedding-aware-neural-diarization","slug":"speaker-embedding-aware-neural-diarization","title":"Speaker Embedding-aware Neural Diarization for Flexible Number of Speakers with Textual Information","date":"2021-11-28","arxiv_id":"2111.13694","repositories_listed":2,"syntology":null},{"url":"/paper/bertraffic-a-robust-bert-based-approach-for","slug":"bertraffic-a-robust-bert-based-approach-for","title":"BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications","date":"2021-10-12","arxiv_id":"2110.05781","repositories_listed":2,"syntology":null},{"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/end-to-end-speaker-segmentation-for-overlap","slug":"end-to-end-speaker-segmentation-for-overlap","title":"End-to-end speaker segmentation for overlap-aware resegmentation","date":"2021-04-08","arxiv_id":"2104.04045","repositories_listed":2,"syntology":null},{"url":"/paper/a-comprehensive-evaluation-of-incremental","slug":"a-comprehensive-evaluation-of-incremental","title":"A Comprehensive Evaluation of Incremental Speech Recognition and Diarization for Conversational AI","date":"2020-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/voxlingua107-a-dataset-for-spoken-language-1","slug":"voxlingua107-a-dataset-for-spoken-language-1","title":"VoxLingua107: a Dataset for Spoken Language Recognition","date":"2020-11-25","arxiv_id":"2011.12998","repositories_listed":2,"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/voxlingua107-a-dataset-for-spoken-language-1#ran","syntology_url":"https://syntology.ai/paper/2011.12998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12998"}},"official":{"repos":["alumae/torch-xvectors-wav"],"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/end-to-end-neural-speaker-diarization-with","slug":"end-to-end-neural-speaker-diarization-with","title":"End-to-End Neural Speaker Diarization with Self-attention","date":"2019-09-13","arxiv_id":"1909.06247","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-neural-speaker-diarization-with#ran","syntology_url":"https://syntology.ai/paper/1909.06247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.06247"}},"official":{"repos":["hitachi-speech/EEND"],"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/ava-activespeaker-an-audio-visual-dataset-for","slug":"ava-activespeaker-an-audio-visual-dataset-for","title":"AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection","date":"2019-01-05","arxiv_id":"1901.01342","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-and-generalizable-speaker","slug":"efficient-and-generalizable-speaker","title":"Efficient and Generalizable Speaker Diarization via Structured Pruning of Self-Supervised Models","date":"2025-06-23","arxiv_id":"2506.18623","repositories_listed":1,"syntology":null},{"url":"/paper/speaker-diarization-with-overlapping","slug":"speaker-diarization-with-overlapping","title":"Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm","date":"2025-06-03","arxiv_id":"2506.02610","repositories_listed":1,"syntology":null},{"url":"/paper/2505-10879","slug":"2505-10879","title":"Multi-Stage Speaker Diarization for Noisy Classrooms","date":"2025-05-16","arxiv_id":"2505.10879","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-speech-segmentation-a-general","slug":"unsupervised-speech-segmentation-a-general","title":"Unsupervised Speech Segmentation: A General Approach Using Speech Language Models","date":"2025-01-07","arxiv_id":"2501.03711","repositories_listed":1,"syntology":null},{"url":"/paper/dicow-diarization-conditioned-whisper-for","slug":"dicow-diarization-conditioned-whisper-for","title":"DiCoW: Diarization-Conditioned Whisper for Target Speaker Automatic Speech Recognition","date":"2024-12-30","arxiv_id":"2501.00114","repositories_listed":1,"syntology":null},{"url":"/paper/automating-feedback-analysis-in-surgical","slug":"automating-feedback-analysis-in-surgical","title":"Automating Feedback Analysis in Surgical Training: Detection, Categorization, and Assessment","date":"2024-12-01","arxiv_id":"2412.00760","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-calibration-of-powerset-speaker","slug":"on-the-calibration-of-powerset-speaker","title":"On the calibration of powerset speaker diarization models","date":"2024-09-24","arxiv_id":"2409.15885","repositories_listed":1,"syntology":null},{"url":"/paper/self-tuning-spectral-clustering-for-speaker","slug":"self-tuning-spectral-clustering-for-speaker","title":"Self-Tuning Spectral Clustering for Speaker Diarization","date":"2024-09-16","arxiv_id":"2410.00023","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-self-supervised-learning-for","slug":"leveraging-self-supervised-learning-for","title":"Leveraging Self-Supervised Learning for Speaker Diarization","date":"2024-09-14","arxiv_id":"2409.09408","repositories_listed":1,"syntology":null},{"url":"/paper/data-efficient-child-adult-speaker","slug":"data-efficient-child-adult-speaker","title":"Data Efficient Child-Adult Speaker Diarization with Simulated Conversations","date":"2024-09-13","arxiv_id":"2409.08881","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/data-efficient-child-adult-speaker#ran","syntology_url":"https://syntology.ai/paper/2409.08881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.08881"}},"official":{"repos":["usc-sail/child-adult-diarization"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sortformer-seamless-integration-of-speaker","slug":"sortformer-seamless-integration-of-speaker","title":"Sortformer: Seamless Integration of Speaker Diarization and ASR by Bridging Timestamps and Tokens","date":"2024-09-10","arxiv_id":"2409.06656","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/exploring-speech-foundation-models-for","slug":"exploring-speech-foundation-models-for","title":"Exploring Speech Foundation Models for Speaker Diarization in Child-Adult Dyadic Interactions","date":"2024-06-12","arxiv_id":"2406.07890","repositories_listed":1,"syntology":null},{"url":"/paper/llm-based-speaker-diarization-correction-a","slug":"llm-based-speaker-diarization-correction-a","title":"LLM-based speaker diarization correction: A generalizable approach","date":"2024-06-07","arxiv_id":"2406.04927","repositories_listed":1,"syntology":null},{"url":"/paper/pixit-joint-training-of-speaker-diarization","slug":"pixit-joint-training-of-speaker-diarization","title":"PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings","date":"2024-03-04","arxiv_id":"2403.02288","repositories_listed":1,"syntology":null},{"url":"/paper/online-speaker-diarization-of-meetings-guided","slug":"online-speaker-diarization-of-meetings-guided","title":"Online speaker diarization of meetings guided by speech separation","date":"2024-01-30","arxiv_id":"2402.00067","repositories_listed":1,"syntology":null},{"url":"/paper/overlap-aware-end-to-end-supervised","slug":"overlap-aware-end-to-end-supervised","title":"End-to-End Supervised Hierarchical Graph Clustering for Speaker Diarization","date":"2024-01-23","arxiv_id":"2401.12850","repositories_listed":1,"syntology":null},{"url":"/paper/multichannel-av-wav2vec2-a-framework-for","slug":"multichannel-av-wav2vec2-a-framework-for","title":"Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation","date":"2024-01-07","arxiv_id":"2401.03468","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":2,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multichannel-av-wav2vec2-a-framework-for#ran","syntology_url":"https://syntology.ai/paper/2401.03468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03468"}},"official":{"repos":["zqs01/multi-channel-wav2vec2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/diaper-end-to-end-neural-diarization-with","slug":"diaper-end-to-end-neural-diarization-with","title":"DiaPer: End-to-End Neural Diarization with Perceiver-Based Attractors","date":"2023-12-07","arxiv_id":"2312.04324","repositories_listed":1,"syntology":null},{"url":"/paper/powerset-multi-class-cross-entropy-loss-for","slug":"powerset-multi-class-cross-entropy-loss-for","title":"Powerset multi-class cross entropy loss for neural speaker diarization","date":"2023-10-19","arxiv_id":"2310.13025","repositories_listed":1,"syntology":null},{"url":"/paper/frame-wise-streaming-end-to-end-speaker","slug":"frame-wise-streaming-end-to-end-speaker","title":"Frame-wise streaming end-to-end speaker diarization with non-autoregressive self-attention-based attractors","date":"2023-09-25","arxiv_id":"2309.13916","repositories_listed":1,"syntology":null},{"url":"/paper/neural-speaker-diarization-using-memory-aware","slug":"neural-speaker-diarization-using-memory-aware","title":"Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding with Sequence-to-Sequence Architecture","date":"2023-09-17","arxiv_id":"2309.09180","repositories_listed":1,"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":2,"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/neural-speaker-diarization-using-memory-aware#ran","syntology_url":"https://syntology.ai/paper/2309.09180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.09180"}},"official":{"repos":["liyunlongaaa/nsd-ms2s"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/diacorrect-error-correction-back-end-for","slug":"diacorrect-error-correction-back-end-for","title":"DiaCorrect: Error Correction Back-end For Speaker Diarization","date":"2023-09-15","arxiv_id":"2309.08377","repositories_listed":1,"syntology":null},{"url":"/paper/diarist-streaming-speech-translation-with","slug":"diarist-streaming-speech-translation-with","title":"DiariST: Streaming Speech Translation with Speaker Diarization","date":"2023-09-14","arxiv_id":"2309.08007","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-speaker-diarization-with-large","slug":"enhancing-speaker-diarization-with-large","title":"Enhancing Speaker Diarization with Large Language Models: A Contextual Beam Search Approach","date":"2023-09-11","arxiv_id":"2309.05248","repositories_listed":1,"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/enhancing-speaker-diarization-with-large#ran","syntology_url":"https://syntology.ai/paper/2309.05248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05248"}},"official":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/neural-diarization-with-non-autoregressive","slug":"neural-diarization-with-non-autoregressive","title":"Neural Diarization with Non-autoregressive Intermediate Attractors","date":"2023-03-13","arxiv_id":"2303.06806","repositories_listed":1,"syntology":null},{"url":"/paper/a-light-weight-model-for-active-speaker","slug":"a-light-weight-model-for-active-speaker","title":"A Light Weight Model for Active Speaker Detection","date":"2023-03-08","arxiv_id":"2303.04439","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-light-weight-model-for-active-speaker#ran","syntology_url":"https://syntology.ai/paper/2303.04439","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.04439"}},"official":{"repos":["junhua-liao/light-asd"],"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":["official"]}}},{"url":"/paper/told-a-novel-two-stage-overlap-aware","slug":"told-a-novel-two-stage-overlap-aware","title":"TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization","date":"2023-03-08","arxiv_id":"2303.05397","repositories_listed":1,"syntology":null},{"url":"/paper/supervised-hierarchical-clustering-using","slug":"supervised-hierarchical-clustering-using","title":"Supervised Hierarchical Clustering using Graph Neural Networks for Speaker Diarization","date":"2023-02-24","arxiv_id":"2302.12716","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/on-out-of-distribution-detection-for-audio","slug":"on-out-of-distribution-detection-for-audio","title":"On Out-of-Distribution Detection for Audio with Deep Nearest Neighbors","date":"2022-10-27","arxiv_id":"2210.15283","repositories_listed":1,"syntology":null},{"url":"/paper/highly-efficient-real-time-streaming-and","slug":"highly-efficient-real-time-streaming-and","title":"Highly Efficient Real-Time Streaming and Fully On-Device Speaker Diarization with Multi-Stage Clustering","date":"2022-10-25","arxiv_id":"2210.13690","repositories_listed":1,"syntology":null},{"url":"/paper/brouhaha-multi-task-training-for-voice","slug":"brouhaha-multi-task-training-for-voice","title":"Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimation","date":"2022-10-24","arxiv_id":"2210.13248","repositories_listed":1,"syntology":null},{"url":"/paper/the-conversational-short-phrase-speaker","slug":"the-conversational-short-phrase-speaker","title":"The Conversational Short-phrase Speaker Diarization (CSSD) Task: Dataset, Evaluation Metric and Baselines","date":"2022-08-17","arxiv_id":"2208.08042","repositories_listed":1,"syntology":null},{"url":"/paper/utterance-by-utterance-overlap-aware-neural","slug":"utterance-by-utterance-overlap-aware-neural","title":"Utterance-by-utterance overlap-aware neural diarization with Graph-PIT","date":"2022-07-28","arxiv_id":"2207.13888","repositories_listed":1,"syntology":null},{"url":"/paper/improving-the-naturalness-of-simulated","slug":"improving-the-naturalness-of-simulated","title":"Improving the Naturalness of Simulated Conversations for End-to-End Neural Diarization","date":"2022-04-24","arxiv_id":"2204.11232","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-speech-separation-for","slug":"leveraging-speech-separation-for","title":"Low-Latency Speech Separation Guided Diarization for Telephone Conversations","date":"2022-04-05","arxiv_id":"2204.02306","repositories_listed":1,"syntology":null},{"url":"/paper/eend-ss-joint-end-to-end-neural-speaker","slug":"eend-ss-joint-end-to-end-neural-speaker","title":"EEND-SS: Joint End-to-End Neural Speaker Diarization and Speech Separation for Flexible Number of Speakers","date":"2022-03-31","arxiv_id":"2203.17068","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/visualizations-of-complex-sequences-of-family","slug":"visualizations-of-complex-sequences-of-family","title":"Visualizations of Complex Sequences of Family-Infant Vocalizations Using Bag-of-Audio-Words Approach Based on Wav2vec 2.0 Features","date":"2022-03-29","arxiv_id":"2203.15183","repositories_listed":1,"syntology":null},{"url":"/paper/speaker-embedding-aware-neural-diarization-a","slug":"speaker-embedding-aware-neural-diarization-a","title":"Speaker Embedding-aware Neural Diarization: an Efficient Framework for Overlapping Speech Diarization in Meeting Scenarios","date":"2022-03-18","arxiv_id":"2203.09767","repositories_listed":1,"syntology":null},{"url":"/paper/turn-to-diarize-online-speaker-diarization","slug":"turn-to-diarize-online-speaker-diarization","title":"Turn-to-Diarize: Online Speaker Diarization Constrained by Transformer Transducer Speaker Turn Detection","date":"2021-09-23","arxiv_id":"2109.11641","repositories_listed":1,"syntology":null},{"url":"/paper/overlap-aware-low-latency-online-speaker","slug":"overlap-aware-low-latency-online-speaker","title":"Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation","date":"2021-09-14","arxiv_id":"2109.06483","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-metric-learning-with-graph","slug":"self-supervised-metric-learning-with-graph","title":"Self-Supervised Metric Learning With Graph Clustering For Speaker Diarization","date":"2021-09-14","arxiv_id":"2109.06824","repositories_listed":1,"syntology":null},{"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/encoder-decoder-based-attractor-calculation","slug":"encoder-decoder-based-attractor-calculation","title":"Encoder-Decoder Based Attractors for End-to-End Neural Diarization","date":"2021-06-20","arxiv_id":"2106.10654","repositories_listed":1,"syntology":null},{"url":"/paper/advances-in-integration-of-end-to-end-neural","slug":"advances-in-integration-of-end-to-end-neural","title":"Advances in integration of end-to-end neural and clustering-based diarization for real conversational speech","date":"2021-05-19","arxiv_id":"2105.09040","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-representation-learning-with","slug":"self-supervised-representation-learning-with","title":"Self-supervised Representation Learning With Path Integral Clustering For Speaker Diarization","date":"2021-04-19","arxiv_id":"2104.09456","repositories_listed":1,"syntology":null},{"url":"/paper/speaker-diarization-using-two-pass-leave-one","slug":"speaker-diarization-using-two-pass-leave-one","title":"Speaker Diarization using Two-pass Leave-One-Out Gaussian PLDA Clustering of DNN Embeddings","date":"2021-04-06","arxiv_id":"2104.02469","repositories_listed":1,"syntology":null},{"url":"/paper/reformulating-dover-lap-label-mapping-as-a","slug":"reformulating-dover-lap-label-mapping-as-a","title":"Reformulating DOVER-Lap Label Mapping as a Graph Partitioning Problem","date":"2021-04-05","arxiv_id":"2104.01954","repositories_listed":1,"syntology":null},{"url":"/paper/data-fusion-for-audiovisual-speaker","slug":"data-fusion-for-audiovisual-speaker","title":"Data Fusion for Audiovisual Speaker Localization: Extending Dynamic Stream Weights to the Spatial Domain","date":"2021-02-23","arxiv_id":"2102.11588","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/learning-disentangled-phone-and-speaker","slug":"learning-disentangled-phone-and-speaker","title":"Learning Disentangled Phone and Speaker Representations in a Semi-Supervised VQ-VAE Paradigm","date":"2020-10-21","arxiv_id":"2010.10727","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-disentangled-phone-and-speaker#ran","syntology_url":"https://syntology.ai/paper/2010.10727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.10727"}},"official":{"repos":["rhoposit/icassp2021"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/speaker-diarization-using-recurrent-neural","slug":"speaker-diarization-using-recurrent-neural","title":"Speaker Diarization: Using Recurrent Neural Networks","date":"2020-06-10","arxiv_id":"2006.05596","repositories_listed":1,"syntology":null},{"url":"/paper/speaker-diarization-as-a-fully-online","slug":"speaker-diarization-as-a-fully-online","title":"Speaker Diarization as a Fully Online Learning Problem in MiniVox","date":"2020-06-08","arxiv_id":"2006.04376","repositories_listed":1,"syntology":null},{"url":"/paper/neural-speaker-diarization-with-speaker-wise","slug":"neural-speaker-diarization-with-speaker-wise","title":"Neural Speaker Diarization with Speaker-Wise Chain Rule","date":"2020-06-02","arxiv_id":"2006.01796","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-speaker-diarization-with-speaker-wise#ran","syntology_url":"https://syntology.ai/paper/2006.01796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.01796"}},"official":{"repos":["hitachi-speech/EEND"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/probabilistic-embeddings-for-speaker","slug":"probabilistic-embeddings-for-speaker","title":"Probabilistic embeddings for speaker diarization","date":"2020-04-06","arxiv_id":"2004.04096","repositories_listed":1,"syntology":{"n":21,"n_ran":19,"n_constructed":0,"n_ran_checked":19,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/probabilistic-embeddings-for-speaker#ran","syntology_url":"https://syntology.ai/paper/2004.04096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04096"}},"official":{"repos":["bsxfan/probabilistic_embeddings"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":19,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/auto-tuning-spectral-clustering-for-speaker","slug":"auto-tuning-spectral-clustering-for-speaker","title":"Auto-Tuning Spectral Clustering for Speaker Diarization Using Normalized Maximum Eigengap","date":"2020-03-05","arxiv_id":"2003.02405","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-neural-diarization-reformulating","slug":"end-to-end-neural-diarization-reformulating","title":"End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label Classification","date":"2020-02-24","arxiv_id":"2003.02966","repositories_listed":1,"syntology":null},{"url":"/paper/speaker-diarization-with-region-proposal","slug":"speaker-diarization-with-region-proposal","title":"Speaker Diarization with Region Proposal Network","date":"2020-02-14","arxiv_id":"2002.06220","repositories_listed":1,"syntology":null},{"url":"/paper/phoneme-boundary-detection-using-learnable","slug":"phoneme-boundary-detection-using-learnable","title":"Phoneme Boundary Detection using Learnable Segmental Features","date":"2020-02-11","arxiv_id":"2002.04992","repositories_listed":1,"syntology":null},{"url":"/paper/supervised-online-diarization-with-sample","slug":"supervised-online-diarization-with-sample","title":"Supervised online diarization with sample mean loss for multi-domain data","date":"2019-11-04","arxiv_id":"1911.01266","repositories_listed":1,"syntology":null},{"url":"/paper/robust-speaker-recognition-using-unsupervised","slug":"robust-speaker-recognition-using-unsupervised","title":"Robust speaker recognition using unsupervised adversarial invariance","date":"2019-11-03","arxiv_id":"1911.00940","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-neural-speaker-diarization-with-1","slug":"end-to-end-neural-speaker-diarization-with-1","title":"End-to-End Neural Speaker Diarization with Permutation-Free Objectives","date":"2019-09-12","arxiv_id":"1909.05952","repositories_listed":1,"syntology":null},{"url":"/paper/lstm-based-similarity-measurement-with","slug":"lstm-based-similarity-measurement-with","title":"LSTM based Similarity Measurement with Spectral Clustering for Speaker Diarization","date":"2019-07-23","arxiv_id":"1907.10393","repositories_listed":1,"syntology":null},{"url":"/paper/ultrasound-tongue-imaging-for-diarization-and","slug":"ultrasound-tongue-imaging-for-diarization-and","title":"Ultrasound tongue imaging for diarization and alignment of child speech therapy sessions","date":"2019-07-01","arxiv_id":"1907.00818","repositories_listed":1,"syntology":null},{"url":"/paper/the-second-dihard-diarization-challenge","slug":"the-second-dihard-diarization-challenge","title":"The Second DIHARD Diarization Challenge: Dataset, task, and baselines","date":"2019-06-18","arxiv_id":"1906.07839","repositories_listed":1,"syntology":null},{"url":"/paper/countnet-estimating-the-number-of-concurrent","slug":"countnet-estimating-the-number-of-concurrent","title":"CountNet: Estimating the Number of Concurrent Speakers Using Supervised Learning Speaker Count Estimation","date":"2018-10-28","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fully-supervised-speaker-diarization","slug":"fully-supervised-speaker-diarization","title":"Fully Supervised Speaker Diarization","date":"2018-10-10","arxiv_id":"1810.04719","repositories_listed":1,"syntology":null},{"url":"/paper/the-eurecom-submission-to-the-first-dihard","slug":"the-eurecom-submission-to-the-first-dihard","title":"The EURECOM Submission to the First DIHARD Challenge","date":"2018-09-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/scalable-adaptation-of-state-complexity-for","slug":"scalable-adaptation-of-state-complexity-for","title":"Scalable Adaptation of State Complexity for Nonparametric Hidden Markov Models","date":"2015-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"exploring-speaker-diarization-with-mixture-of","title":"Exploring Speaker Diarization with Mixture of Experts","date":"2025-06-17","arxiv_id":"2506.14750","repositories_listed":0,"syntology":null},{"url":null,"slug":"m3sd-multi-modal-multi-scenario-and-multi","title":"M3SD: Multi-modal, Multi-scenario and Multi-language Speaker Diarization Dataset","date":"2025-06-17","arxiv_id":"2506.14427","repositories_listed":0,"syntology":null},{"url":null,"slug":"seewo-s-submission-to-mlc-slm-lessons-learned","title":"Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models","date":"2025-06-16","arxiv_id":"2506.13300","repositories_listed":0,"syntology":null},{"url":null,"slug":"sc-sot-conditioning-the-decoder-on-diarized","title":"SC-SOT: Conditioning the Decoder on Diarized Speaker Information for End-to-End Overlapped Speech Recognition","date":"2025-06-15","arxiv_id":"2506.12672","repositories_listed":0,"syntology":null},{"url":null,"slug":"diarization-aware-multi-speaker-automatic","title":"Diarization-Aware Multi-Speaker Automatic Speech Recognition via Large Language Models","date":"2025-06-06","arxiv_id":"2506.05796","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-neural-diarization-through-speaker","title":"Improving Neural Diarization through Speaker Attribute Attractors and Local Dependency Modeling","date":"2025-06-05","arxiv_id":"2506.05593","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tune-before-structured-pruning-towards","title":"Fine-tune Before Structured Pruning: Towards Compact and Accurate Self-Supervised Models for Speaker Diarization","date":"2025-05-30","arxiv_id":"2505.24111","repositories_listed":0,"syntology":null}],"syntology_records":14,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":14,"papers_where_code_ran_first_page":"/task/speaker-diarization/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":4,"url":"/task/speaker-diarization/papers/2","json":"/task/speaker-diarization/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/speaker-diarization/papers/3","json":"/task/speaker-diarization/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/speaker-diarization/papers/4","json":"/task/speaker-diarization/papers/4.json","rows":28},{"order":"ran","page":1,"of":1,"url":"/task/speaker-diarization/papers/ran/1","json":"/task/speaker-diarization/papers/ran/1.json","rows":14}],"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":"7f0a3790ee64223ff67146b76238731d40ffb2b492928d3394bfadceef920681","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}