{"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/speech-extraction","name":"Speech Extraction","slug":"speech-extraction","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":48,"papers_with_code":10,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/speech-extraction-on-wsj0-2mix-extr","slug":"speech-extraction-on-wsj0-2mix-extr","dataset":"WSJ0-2mix-extr","dataset_url":"/dataset/wsj0-2mix-extr","rows_in_archive":1,"metrics":["SI-SDR"],"first_row_in_archive_order":{"model":"SpEx+ (tied)","paper_title":"SpEx+: A Complete Time Domain Speaker Extraction Network","paper_url":null,"paper_date":"2020-05-10","arxiv_id":"2005.04686","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/wsj0-2mix-extr","name":"WSJ0-2mix-extr","full_name":"","num_papers_in_archive":6},{"url":"/dataset/mc-grid-test","name":"MC_GRID","full_name":"Multi_Channel_Grid","num_papers_in_archive":1},{"url":"/dataset/whamr-ext","name":"WHAMR_ext","full_name":"WHAMR_ext","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/speech-separation","name":"Speech Separation"}],"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":1,"rows_per_page":100,"shown":48,"of":48,"of_with_code":10,"tagged_in_all":48,"counts":{"archive_papers_tagged":48,"with_a_code_link":10,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":48,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":0,"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 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/solospeech-enhancing-intelligibility-and","slug":"solospeech-enhancing-intelligibility-and","title":"SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline","date":"2025-05-25","arxiv_id":"2505.19314","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-speaker-identity-text-guided-target","slug":"beyond-speaker-identity-text-guided-target","title":"Beyond Speaker Identity: Text Guided Target Speech Extraction","date":"2025-01-15","arxiv_id":"2501.09169","repositories_listed":1,"syntology":null},{"url":"/paper/generative-speech-foundation-model","slug":"generative-speech-foundation-model","title":"Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration","date":"2024-09-24","arxiv_id":"2409.16117","repositories_listed":1,"syntology":null},{"url":"/paper/look-once-to-hear-target-speech-hearing-with","slug":"look-once-to-hear-target-speech-hearing-with","title":"Look Once to Hear: Target Speech Hearing with Noisy Examples","date":"2024-05-10","arxiv_id":"2405.06289","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":2,"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/look-once-to-hear-target-speech-hearing-with#ran","syntology_url":"https://syntology.ai/paper/2405.06289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06289"}},"official":{"repos":["vb000/lookoncetohear"],"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/neural-target-speech-extraction-an-overview","slug":"neural-target-speech-extraction-an-overview","title":"Neural Target Speech Extraction: An Overview","date":"2023-01-31","arxiv_id":"2301.13341","repositories_listed":1,"syntology":null},{"url":"/paper/analysis-of-impact-of-emotions-on-target","slug":"analysis-of-impact-of-emotions-on-target","title":"Analysis of impact of emotions on target speech extraction and speech separation","date":"2022-08-15","arxiv_id":"2208.07091","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-role-of-spatial-spectral-and-temporal","slug":"on-the-role-of-spatial-spectral-and-temporal","title":"On the Role of Spatial, Spectral, and Temporal Processing for DNN-based Non-linear Multi-channel Speech Enhancement","date":"2022-06-22","arxiv_id":"2206.11181","repositories_listed":1,"syntology":null},{"url":"/paper/dpccn-densely-connected-pyramid-complex","slug":"dpccn-densely-connected-pyramid-complex","title":"DPCCN: Densely-Connected Pyramid Complex Convolutional Network for Robust Speech Separation And Extraction","date":"2021-12-27","arxiv_id":"2112.13520","repositories_listed":1,"syntology":null},{"url":"/paper/blind-source-extraction-based-on-multi","slug":"blind-source-extraction-based-on-multi","title":"Target Speech Extraction Based on Blind Source Separation and X-vector-based Speaker Selection Trained with Data Augmentation","date":"2020-05-16","arxiv_id":"2005.07976","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":null,"slug":"incorporating-linguistic-constraints-from","title":"Incorporating Linguistic Constraints from External Knowledge Source for Audio-Visual Target Speech Extraction","date":"2025-06-11","arxiv_id":"2506.09792","repositories_listed":0,"syntology":null},{"url":null,"slug":"inter-speaker-relative-cues-for-text-guided","title":"Inter-Speaker Relative Cues for Text-Guided Target Speech Extraction","date":"2025-06-02","arxiv_id":"2506.01483","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-channel-target-speech-extraction","title":"Single-Channel Target Speech Extraction Utilizing Distance and Room Clues","date":"2025-05-20","arxiv_id":"2505.14433","repositories_listed":0,"syntology":null},{"url":null,"slug":"sonicsieve-bringing-directional-speech","title":"SonicSieve: Bringing Directional Speech Extraction to Smartphones Using Acoustic Microstructures","date":"2025-04-15","arxiv_id":"2504.10793","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-speech-extraction-leveraging","title":"Contextual Speech Extraction: Leveraging Textual History as an Implicit Cue for Target Speech Extraction","date":"2025-03-11","arxiv_id":"2503.08798","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-intelligibility-for-generative","title":"Enhancing Intelligibility for Generative Target Speech Extraction via Joint Optimization with Target Speaker ASR","date":"2025-01-24","arxiv_id":"2501.14477","repositories_listed":0,"syntology":null},{"url":null,"slug":"distance-based-single-channel-target-speech","title":"Distance Based Single-Channel Target Speech Extraction","date":"2024-12-28","arxiv_id":"2412.20144","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigation-of-speaker-representation-for","title":"Investigation of Speaker Representation for Target-Speaker Speech Processing","date":"2024-10-15","arxiv_id":"2410.11243","repositories_listed":0,"syntology":null},{"url":null,"slug":"separate-in-the-speech-chain-cross-modal","title":"Separate in the Speech Chain: Cross-Modal Conditional Audio-Visual Target Speech Extraction","date":"2024-04-19","arxiv_id":"2404.12725","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-self-supervised-learning-models-with","title":"Probing Self-supervised Learning Models with Target Speech Extraction","date":"2024-02-17","arxiv_id":"2402.13200","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-speech-extraction-with-pre-trained","title":"Target Speech Extraction with Pre-trained Self-supervised Learning Models","date":"2024-02-17","arxiv_id":"2402.13199","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-disentangled-representation-2","title":"Self-Supervised Disentangled Representation Learning for Robust Target Speech Extraction","date":"2023-12-16","arxiv_id":"2312.10305","repositories_listed":0,"syntology":null},{"url":null,"slug":"scenario-aware-audio-visual-tf-gridnet-for","title":"Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction","date":"2023-10-30","arxiv_id":"2310.19644","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoprep-an-automatic-preprocessing-framework","title":"AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data","date":"2023-09-25","arxiv_id":"2309.13905","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-conditional-expectation-model-for","title":"DDTSE: Discriminative Diffusion Model for Target Speech Extraction","date":"2023-09-25","arxiv_id":"2309.13874","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-speech-extraction-with-conditional","title":"Target Speech Extraction with Conditional Diffusion Model","date":"2023-08-08","arxiv_id":"2308.03987","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-neural-beamformer-with-spatial","title":"Enhanced Neural Beamformer with Spatial Information for Target Speech Extraction","date":"2023-06-28","arxiv_id":"2306.15942","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-speech-enhancement-with","title":"Audio-Visual Speech Enhancement With Selective Off-Screen Speech Extraction","date":"2023-06-10","arxiv_id":"2306.06495","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-neural-transducer","title":"Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data","date":"2023-05-25","arxiv_id":"2305.15971","repositories_listed":0,"syntology":null},{"url":null,"slug":"x-sepformer-end-to-end-speaker-extraction","title":"X-SepFormer: End-to-end Speaker Extraction Network with Explicit Optimization on Speaker Confusion","date":"2023-03-09","arxiv_id":"2303.05023","repositories_listed":0,"syntology":null},{"url":null,"slug":"quotations-coreference-resolution-and","title":"Quotations, Coreference Resolution, and Sentiment Annotations in Croatian News Articles: An Exploratory Study","date":"2022-12-14","arxiv_id":"2212.07172","repositories_listed":0,"syntology":null},{"url":null,"slug":"streaming-end-to-end-target-speaker-asr","title":"Streaming Target-Speaker ASR with Neural Transducer","date":"2022-09-09","arxiv_id":"2209.04175","repositories_listed":0,"syntology":null},{"url":null,"slug":"conceptbeam-concept-driven-target-speech","title":"ConceptBeam: Concept Driven Target Speech Extraction","date":"2022-07-25","arxiv_id":"2207.11964","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-path-attention-is-all-you-need-for-audio","title":"Dual-Path Cross-Modal Attention for better Audio-Visual Speech Extraction","date":"2022-07-09","arxiv_id":"2207.04213","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneous-speech-extraction-for-multiple","title":"Simultaneous Speech Extraction for Multiple Target Speakers under the Meeting Scenarios","date":"2022-06-17","arxiv_id":"2206.08525","repositories_listed":0,"syntology":null},{"url":null,"slug":"strategies-to-improve-robustness-of-target","title":"Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations","date":"2022-06-16","arxiv_id":"2206.08174","repositories_listed":0,"syntology":null},{"url":null,"slug":"listen-only-to-me-how-well-can-target-speech","title":"Listen only to me! How well can target speech extraction handle false alarms?","date":"2022-04-11","arxiv_id":"2204.04811","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-joint-control-of-acoustic","title":"Deep Learning-Based Joint Control of Acoustic Echo Cancellation, Beamforming and Postfiltering","date":"2022-03-03","arxiv_id":"2203.01793","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-based-personal-speech-enhancement","title":"Learning-based personal speech enhancement for teleconferencing by exploiting spatial-spectral features","date":"2021-12-10","arxiv_id":"2112.05686","repositories_listed":0,"syntology":null},{"url":null,"slug":"blind-extraction-of-target-speech-source","title":"Target Speech Extraction: Independent Vector Extraction Guided by Supervised Speaker Identification","date":"2021-11-05","arxiv_id":"2111.03482","repositories_listed":0,"syntology":null},{"url":null,"slug":"all-neural-beamformer-for-continuous-speech","title":"All-neural beamformer for continuous speech separation","date":"2021-10-13","arxiv_id":"2110.06428","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-channel-decorrelation-for-multi","title":"Improving Channel Decorrelation for Multi-Channel Target Speech Extraction","date":"2021-06-06","arxiv_id":"2106.03113","repositories_listed":0,"syntology":null},{"url":null,"slug":"time-domain-speech-extraction-with-spatial","title":"Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism","date":"2021-02-07","arxiv_id":"2102.03762","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-activity-driven-neural-speech","title":"Speaker activity driven neural speech extraction","date":"2021-01-14","arxiv_id":"2101.05516","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-separation-using-speaker-inventories","title":"Speaker Separation Using Speaker Inventories and Estimated Speech","date":"2020-10-20","arxiv_id":"2010.10556","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-based-scaling-adaptation-for-target","title":"Attention-based scaling adaptation for target speech extraction","date":"2020-10-19","arxiv_id":"2010.10923","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-talker-asr-for-an-unknown-number-of","title":"Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR","date":"2020-06-04","arxiv_id":"2006.02786","repositories_listed":0,"syntology":null},{"url":null,"slug":"quick-algorithms-for-independent-vector","title":"Algorithm for Independent Vector Extraction Based on Semi-Time-Variant Mixing Model","date":"2019-10-22","arxiv_id":"1910.10242","repositories_listed":0,"syntology":null}],"syntology_records":1,"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":1,"papers_where_code_ran_first_page":"/task/speech-extraction/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":"ran","page":1,"of":1,"url":"/task/speech-extraction/papers/ran/1","json":"/task/speech-extraction/papers/ran/1.json","rows":1}],"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":"267f4dc88e86fd1a03cb6b94f9ef247f871d51d8dae9a5cd7b8d6627bb69c36d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}