{"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":"/dataset/callhome-american-english-speech","name":"CALLHOME American English Speech","full_name":null,"description_markdown":"The CALLHOME English Corpus is a collection of unscripted telephone conversations between native speakers of English. Here are the key details:\r\n\r\nParticipants: 120 individuals.\r\nType of Study: Naturalistic.\r\nLocation: USA.\r\nMedia Type: Audio.\r\nDOI: doi:10.21415/T5KP54.\r\nContents: The corpus contains 120 telephone conversations, each lasting up to 30 minutes.\r\nOrigins: All calls originated in North America, with 90 calls placed to various locations overseas and 30 calls within North America.\r\nTranscripts: The transcripts cover contiguous 5 or 10-minute segments from recorded conversations.\r\nSpeaker Awareness: All speakers were aware that they were being recorded.\r\nTopics: Participants had no guidelines on what to talk about; most called family members or close friends overseas.\r\nPurpose: Collected primarily to support the project on Large Vocabulary Conversational Speech Recognition (LVCSR), sponsored by the U.S. Department of Defense.","description_withheld":null,"homepage":"https://catalog.ldc.upenn.edu/LDC97S42","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Automatic Speech Recognition","url":"/task/automatic-speech-recognition-2","datasets_with_task":"/datasets/task/automatic-speech-recognition-2"},{"name":"Speaker Diarization","url":"/task/speaker-diarization","datasets_with_task":"/datasets/task/speaker-diarization"},{"name":"Speaker Verification","url":"/task/speaker-verification","datasets_with_task":"/datasets/task/speaker-verification"}],"languages":[],"variants":["Switchboard CallHome","Hub5'00 CallHome","CALLHOME Spanish Speech (Test)","CALLHOME Spanish Speech (Dev)","CALLHOME Spanish Speech","CALLHOME-109","CALLHOME","CALLHOME American English Speech"],"data_loaders":[],"num_papers_in_archive":11,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speaker-diarization-on-callhome","task":"Speaker Diarization","dataset_variant":"CALLHOME","rows":10,"metrics":["DER(%)","DER(ig olp)","FA","MI","CF"],"first_row_in_archive_order":{"model":"TOLD","paper":"/paper/told-a-novel-two-stage-overlap-aware","metrics":{"CF":"2.94","DER(%)":"10.14","DER(ig olp)":"7.37","FA":"2.4","MI":"4.8"},"code_links":[{"title":"alibaba-damo-academy/FunASR","url":"https://github.com/alibaba-damo-academy/FunASR"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speaker-diarization-on-callhome-109","task":"Speaker Diarization","dataset_variant":"CALLHOME-109","rows":2,"metrics":["DER(%)"],"first_row_in_archive_order":{"model":"titanet-s","paper":"/paper/titanet-neural-model-for-speaker","metrics":{"DER(%)":"1.11"},"code_links":[{"title":"NVIDIA/NeMo","url":"https://github.com/NVIDIA/NeMo"},{"title":"Wadaboa/titanet","url":"https://github.com/Wadaboa/titanet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speaker-verification-on-callhome","task":"Speaker Verification","dataset_variant":"CALLHOME","rows":2,"metrics":["Cosine EER"],"first_row_in_archive_order":{"model":"GE2E","paper":"/paper/generalized-end-to-end-loss-for-speaker","metrics":{"Cosine EER":"3.55"},"code_links":[{"title":"CorentinJ/Real-Time-Voice-Cloning","url":"https://github.com/CorentinJ/Real-Time-Voice-Cloning"},{"title":"coqui-ai/TTS","url":"https://github.com/coqui-ai/TTS"},{"title":"PaddlePaddle/PaddleSpeech","url":"https://github.com/PaddlePaddle/PaddleSpeech"},{"title":"resemble-ai/Resemblyzer","url":"https://github.com/resemble-ai/Resemblyzer"},{"title":"HarryVolek/PyTorch_Speaker_Verification","url":"https://github.com/HarryVolek/PyTorch_Speaker_Verification"},{"title":"google/speaker-id","url":"https://github.com/google/speaker-id/tree/master/lingvo"},{"title":"JanhHyun/Speaker_Verification","url":"https://github.com/JanhHyun/Speaker_Verification"},{"title":"Janghyun1230/Speaker_Verification","url":"https://github.com/Janghyun1230/Speaker_Verification"},{"title":"yistLin/dvector","url":"https://github.com/yistLin/dvector"},{"title":"rf5/simple-speaker-embedding","url":"https://github.com/rf5/simple-speaker-embedding"},{"title":"cvqluu/GE2E-Loss","url":"https://github.com/cvqluu/GE2E-Loss"},{"title":"Suhee05/Text-Independent-Speaker-Verification","url":"https://github.com/Suhee05/Text-Independent-Speaker-Verification"},{"title":"Aurora11111/voiceprint","url":"https://github.com/Aurora11111/voiceprint"},{"title":"Aurora11111/speaker-recognition-pytorch","url":"https://github.com/Aurora11111/speaker-recognition-pytorch"},{"title":"muskang48/Speaker-Diarization","url":"https://github.com/muskang48/Speaker-Diarization"},{"title":"tigthor/Voice-Cloning-AI","url":"https://github.com/tigthor/Voice-Cloning-AI"},{"title":"piotrkawa/audio-deepfake-source-tracing","url":"https://github.com/piotrkawa/audio-deepfake-source-tracing"},{"title":"JeffT13/rd-diarization","url":"https://github.com/JeffT13/rd-diarization"},{"title":"gkv856/speaker_embedding_GE2E_loss","url":"https://github.com/gkv856/speaker_embedding_GE2E_loss"},{"title":"dalonlobo/diarization-experiments","url":"https://github.com/dalonlobo/diarization-experiments"},{"title":"luomingshuang/GE2E-SV-TI-Voxceleb-LMS","url":"https://github.com/luomingshuang/GE2E-SV-TI-Voxceleb-LMS"},{"title":"yui-mhcp/base_dl_project","url":"https://github.com/yui-mhcp/base_dl_project"},{"title":"luomingshuang/GE2E-SV-TI-Timit-LMS","url":"https://github.com/luomingshuang/GE2E-SV-TI-Timit-LMS"},{"title":"aijianiula0601/ge2eloss-svf","url":"https://github.com/aijianiula0601/ge2eloss-svf"},{"title":"luomingshuang/GE2E-SV-TI-thchs30-LMS","url":"https://github.com/luomingshuang/GE2E-SV-TI-thchs30-LMS"},{"title":"JeffT13/VoiceEncoder","url":"https://github.com/JeffT13/VoiceEncoder"},{"title":"hanqingguo/GE2E","url":"https://github.com/hanqingguo/GE2E"},{"title":"zhangmin4215/PyTorch_Speaker_Verification","url":"https://github.com/zhangmin4215/PyTorch_Speaker_Verification"},{"title":"icewing1996/baseline","url":"https://github.com/icewing1996/baseline"},{"title":"luomingshuang/GE2E-SV-TI-Chinese-LMS","url":"https://github.com/luomingshuang/GE2E-SV-TI-Chinese-LMS"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speaker-diarization-on-hub5-00-callhome","task":"Speaker Diarization","dataset_variant":"Hub5'00 CallHome","rows":1,"metrics":["V"],"first_row_in_archive_order":{"model":"UIS-RNN","paper":"/paper/fully-supervised-speaker-diarization","metrics":{"V":"10.6"},"code_links":[{"title":"google/uis-rnn","url":"https://github.com/google/uis-rnn"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-callhome-spanish-speech","task":"Speech Recognition","dataset_variant":"CALLHOME Spanish Speech","rows":1,"metrics":["WER"],"first_row_in_archive_order":{"model":"TDT 0-2","paper":"/paper/efficient-sequence-transduction-by-jointly","metrics":{"WER":"17.95"},"code_links":[{"title":"NVIDIA/NeMo","url":"https://github.com/NVIDIA/NeMo"},{"title":"chimechallenge/C8DASR-Baseline-NeMo","url":"https://github.com/chimechallenge/C8DASR-Baseline-NeMo"},{"title":"kehanlu/Nemo","url":"https://github.com/kehanlu/Nemo"},{"title":"wd929/NeMo","url":"https://github.com/wd929/NeMo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-hub500-callhome","task":"Speech Recognition","dataset_variant":"Hub5'00 CallHome","rows":1,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"Espresso","paper":"/paper/espresso-a-fast-end-to-end-neural-speech","metrics":{"Word Error Rate (WER)":"19.1"},"code_links":[{"title":"freewym/espresso","url":"https://github.com/freewym/espresso"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-switchboard-callhome","task":"Speech Recognition","dataset_variant":"Switchboard CallHome","rows":1,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"SpeechStew (100M)","paper":"/paper/speechstew-simply-mix-all-available-speech","metrics":{"Word Error Rate (WER)":"8.3"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":11,"of":11,"counts":{"papers_with_a_benchmark_row":11,"with_a_code_link":10,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":11,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":1,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/efficient-sequence-transduction-by-jointly","slug":"efficient-sequence-transduction-by-jointly","title":"Efficient Sequence Transduction by Jointly Predicting Tokens and Durations","date":"2023-04-13","arxiv_id":"2304.06795","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/efficient-sequence-transduction-by-jointly#ran","syntology_url":"https://syntology.ai/paper/2304.06795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.06795"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/speechstew-simply-mix-all-available-speech","slug":"speechstew-simply-mix-all-available-speech","title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","date":"2021-04-05","arxiv_id":"2104.02133","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/espresso-a-fast-end-to-end-neural-speech","slug":"espresso-a-fast-end-to-end-neural-speech","title":"Espresso: A Fast End-to-end Neural Speech Recognition Toolkit","date":"2019-09-18","arxiv_id":"1909.08723","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["freewym/espresso"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/espresso-a-fast-end-to-end-neural-speech#ran","syntology_url":"https://syntology.ai/paper/1909.08723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.08723"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fully-supervised-speaker-diarization","slug":"fully-supervised-speaker-diarization","title":"Fully Supervised Speaker Diarization","date":"2018-10-10","arxiv_id":"1810.04719","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/generalized-end-to-end-loss-for-speaker","slug":"generalized-end-to-end-loss-for-speaker","title":"Generalized End-to-End Loss for Speaker Verification","date":"2017-10-28","arxiv_id":"1710.10467","rows_on_this_dataset":2,"code_links":30,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":27,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":2,"samples_unverified":8,"pointer_only_for_licence":2,"official":{"repos":["google/speaker-id"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/generalized-end-to-end-loss-for-speaker#ran","syntology_url":"https://syntology.ai/paper/1710.10467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10467"}}}},{"paper":"/paper/speaker-diarization-with-lstm","slug":"speaker-diarization-with-lstm","title":"Speaker Diarization with LSTM","date":"2017-10-28","arxiv_id":"1710.10468","rows_on_this_dataset":1,"code_links":4,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/efficient-sequence-transduction-by-jointly","slug":"efficient-sequence-transduction-by-jointly","title":"Efficient Sequence Transduction by Jointly Predicting Tokens and Durations","date":"2023-04-13","arxiv_id":"2304.06795","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/efficient-sequence-transduction-by-jointly#ran","syntology_url":"https://syntology.ai/paper/2304.06795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.06795"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/speechstew-simply-mix-all-available-speech","slug":"speechstew-simply-mix-all-available-speech","title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","date":"2021-04-05","arxiv_id":"2104.02133","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/espresso-a-fast-end-to-end-neural-speech","slug":"espresso-a-fast-end-to-end-neural-speech","title":"Espresso: A Fast End-to-end Neural Speech Recognition Toolkit","date":"2019-09-18","arxiv_id":"1909.08723","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["freewym/espresso"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/espresso-a-fast-end-to-end-neural-speech#ran","syntology_url":"https://syntology.ai/paper/1909.08723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.08723"}}}},{"paper":"/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","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fully-supervised-speaker-diarization","slug":"fully-supervised-speaker-diarization","title":"Fully Supervised Speaker Diarization","date":"2018-10-10","arxiv_id":"1810.04719","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/generalized-end-to-end-loss-for-speaker","slug":"generalized-end-to-end-loss-for-speaker","title":"Generalized End-to-End Loss for Speaker Verification","date":"2017-10-28","arxiv_id":"1710.10467","rows_on_this_dataset":2,"code_links":30,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":27,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":2,"samples_unverified":8,"pointer_only_for_licence":2,"official":{"repos":["google/speaker-id"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/generalized-end-to-end-loss-for-speaker#ran","syntology_url":"https://syntology.ai/paper/1710.10467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10467"}}}},{"paper":"/paper/speaker-diarization-with-lstm","slug":"speaker-diarization-with-lstm","title":"Speaker Diarization with LSTM","date":"2017-10-28","arxiv_id":"1710.10468","rows_on_this_dataset":1,"code_links":4,"syntology":null}],"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/dataset/callhome-american-english-speech/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/callhome-american-english-speech/papers/ran/1","json":"/dataset/callhome-american-english-speech/papers/ran/1.json","rows":5}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":5,"samples_harvested":39,"samples_ran":30,"samples_constructed":0,"samples_ran_checked":27,"samples_ran_instrument_failed":3,"samples_unverified":9,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":5,"papers_with_a_run_with_no_instrument_failure":4,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"cffdbf069a1968d3f91ed5bafa2756dc280169c948515bf6be54dd26bea05c58","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}