{"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/target-speaker-extraction","name":"Target Speaker Extraction","slug":"target-speaker-extraction","description_markdown":"Extract the dialogue content of the specified target in a multi-person dialogue.","categories":[{"name":"Audio","url":"/area/audio"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":55,"papers_with_code":20,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/speech-recognition","name":"Speech Recognition"}],"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":55,"of":55,"of_with_code":20,"tagged_in_all":55,"counts":{"archive_papers_tagged":55,"with_a_code_link":20,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":55,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/gpu-accelerated-guided-source-separation-for","slug":"gpu-accelerated-guided-source-separation-for","title":"GPU-accelerated Guided Source Separation for Meeting Transcription","date":"2022-12-10","arxiv_id":"2212.05271","repositories_listed":2,"syntology":null},{"url":"/paper/m3anet-multi-scale-and-multi-modal-alignment","slug":"m3anet-multi-scale-and-multi-modal-alignment","title":"M3ANet: Multi-scale and Multi-Modal Alignment Network for Brain-Assisted Target Speaker Extraction","date":"2025-05-31","arxiv_id":"2506.00466","repositories_listed":1,"syntology":{"n":41,"n_ran":30,"n_constructed":23,"n_ran_checked":28,"n_instrument":2,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":28,"n_pointer_only":41,"phrase":"30 ran (of which 23 constructed an object rather than computing a result; 28 with no instrument failure: 0 honoured, 0 violated, 28 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/m3anet-multi-scale-and-multi-modal-alignment#ran","syntology_url":"https://syntology.ai/paper/2506.00466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.00466"}},"official":{"repos":["fchest/m3anet"],"state":"official (archive's flag): 30 ran","n_ran":30,"n_constructed":23,"n_ran_no_instrument_failure":28,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/lauratse-target-speaker-extraction-using-auto","slug":"lauratse-target-speaker-extraction-using-auto","title":"LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Models","date":"2025-04-10","arxiv_id":"2504.07402","repositories_listed":1,"syntology":null},{"url":"/paper/metis-a-foundation-speech-generation-model","slug":"metis-a-foundation-speech-generation-model","title":"Metis: A Foundation Speech Generation Model with Masked Generative Pre-training","date":"2025-02-05","arxiv_id":"2502.03128","repositories_listed":1,"syntology":null},{"url":"/paper/multi-level-speaker-representation-for-target","slug":"multi-level-speaker-representation-for-target","title":"Multi-Level Speaker Representation for Target Speaker Extraction","date":"2024-10-21","arxiv_id":"2410.16059","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/wesep-a-scalable-and-flexible-toolkit-towards","slug":"wesep-a-scalable-and-flexible-toolkit-towards","title":"WeSep: A Scalable and Flexible Toolkit Towards Generalizable Target Speaker Extraction","date":"2024-09-24","arxiv_id":"2409.15799","repositories_listed":1,"syntology":null},{"url":"/paper/tselm-target-speaker-extraction-using","slug":"tselm-target-speaker-extraction-using","title":"TSELM: Target Speaker Extraction using Discrete Tokens and Language Models","date":"2024-09-12","arxiv_id":"2409.07841","repositories_listed":1,"syntology":null},{"url":"/paper/usef-tse-universal-speaker-embedding-free","slug":"usef-tse-universal-speaker-embedding-free","title":"USEF-TSE: Universal Speaker Embedding Free Target Speaker Extraction","date":"2024-09-04","arxiv_id":"2409.02615","repositories_listed":1,"syntology":null},{"url":"/paper/spectron-target-speaker-extraction-using","slug":"spectron-target-speaker-extraction-using","title":"Spectron: Target Speaker Extraction using Conditional Transformer with Adversarial Refinement","date":"2024-09-02","arxiv_id":"2409.01352","repositories_listed":1,"syntology":null},{"url":"/paper/av-crossnet-an-audiovisual-complex-spectral","slug":"av-crossnet-an-audiovisual-complex-spectral","title":"AV-CrossNet: an Audiovisual Complex Spectral Mapping Network for Speech Separation By Leveraging Narrow- and Cross-Band Modeling","date":"2024-06-17","arxiv_id":"2406.11619","repositories_listed":1,"syntology":null},{"url":"/paper/audio-visual-target-speaker-extraction-with","slug":"audio-visual-target-speaker-extraction-with","title":"Audio-Visual Target Speaker Extraction with Reverse Selective Auditory Attention","date":"2024-04-29","arxiv_id":"2404.18501","repositories_listed":1,"syntology":null},{"url":"/paper/typing-to-listen-at-the-cocktail-party-text","slug":"typing-to-listen-at-the-cocktail-party-text","title":"Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction","date":"2023-10-11","arxiv_id":"2310.07284","repositories_listed":1,"syntology":null},{"url":"/paper/rtfs-net-recurrent-time-frequency-modelling","slug":"rtfs-net-recurrent-time-frequency-modelling","title":"RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation","date":"2023-09-29","arxiv_id":"2309.17189","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/rtfs-net-recurrent-time-frequency-modelling#ran","syntology_url":"https://syntology.ai/paper/2309.17189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17189"}},"official":{"repos":["spkgyk/RTFS-Net"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/imaginenet-target-speaker-extraction-with","slug":"imaginenet-target-speaker-extraction-with","title":"ImagineNET: Target Speaker Extraction with Intermittent Visual Cue through Embedding Inpainting","date":"2022-10-31","arxiv_id":"2211.00109","repositories_listed":1,"syntology":null},{"url":"/paper/a-hybrid-continuity-loss-to-reduce-over","slug":"a-hybrid-continuity-loss-to-reduce-over","title":"A Hybrid Continuity Loss to Reduce Over-Suppression for Time-domain Target Speaker Extraction","date":"2022-03-31","arxiv_id":"2203.16843","repositories_listed":1,"syntology":null},{"url":"/paper/l-spex-localized-target-speaker-extraction","slug":"l-spex-localized-target-speaker-extraction","title":"L-SpEx: Localized Target Speaker Extraction","date":"2022-02-21","arxiv_id":"2202.09995","repositories_listed":1,"syntology":null},{"url":"/paper/selective-hearing-through-lip-reading","slug":"selective-hearing-through-lip-reading","title":"Selective Listening by Synchronizing Speech with Lips","date":"2021-06-14","arxiv_id":"2106.07150","repositories_listed":1,"syntology":null},{"url":"/paper/target-speaker-verification-with-selective","slug":"target-speaker-verification-with-selective","title":"Target Speaker Verification with Selective Auditory Attention for Single and Multi-talker Speech","date":"2021-03-30","arxiv_id":"2103.16269","repositories_listed":1,"syntology":null},{"url":"/paper/muse-multi-modal-target-speaker-extraction","slug":"muse-multi-modal-target-speaker-extraction","title":"Muse: Multi-modal target speaker extraction with visual cues","date":"2020-10-15","arxiv_id":"2010.07775","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":"flowtse-target-speaker-extraction-with-flow","title":"FlowTSE: Target Speaker Extraction with Flow Matching","date":"2025-05-20","arxiv_id":"2505.14465","repositories_listed":0,"syntology":null},{"url":null,"slug":"listen-to-extract-onset-prompted-target","title":"Listen to Extract: Onset-Prompted Target Speaker Extraction","date":"2025-05-08","arxiv_id":"2505.05114","repositories_listed":0,"syntology":null},{"url":null,"slug":"c-2-av-tse-context-and-confidence-aware-audio","title":"$C^2$AV-TSE: Context and Confidence-aware Audio Visual Target Speaker Extraction","date":"2025-04-01","arxiv_id":"2504.00750","repositories_listed":0,"syntology":null},{"url":"/paper/target-speaker-extraction-through-comparing","slug":"target-speaker-extraction-through-comparing","title":"Target Speaker Extraction through Comparing Noisy Positive and Negative Audio Enrollments","date":"2025-02-23","arxiv_id":"2502.16611","repositories_listed":0,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/target-speaker-extraction-through-comparing#ran","syntology_url":"https://syntology.ai/paper/2502.16611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.16611"}},"official":null}},{"url":null,"slug":"anyenhance-a-unified-generative-model-with","title":"AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement","date":"2025-01-26","arxiv_id":"2501.15417","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-speaker-embedding-free-target","title":"Universal Speaker Embedding Free Target Speaker Extraction and Personal Voice Activity Detection","date":"2025-01-07","arxiv_id":"2501.03612","repositories_listed":0,"syntology":null},{"url":null,"slug":"momuse-momentum-multi-modal-target-speaker","title":"MoMuSE: Momentum Multi-modal Target Speaker Extraction for Real-time Scenarios with Impaired Visual Cues","date":"2024-12-11","arxiv_id":"2412.08247","repositories_listed":0,"syntology":null},{"url":null,"slug":"stcon-system-for-the-chime-8-challenge","title":"STCON System for the CHiME-8 Challenge","date":"2024-10-17","arxiv_id":"2410.13411","repositories_listed":0,"syntology":null},{"url":"/paper/wanna-hear-your-voice-adaptive-effective-and","slug":"wanna-hear-your-voice-adaptive-effective-and","title":"Wanna hear your voice? A sample is all we need!","date":"2024-10-01","arxiv_id":"2410.00527","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-stage-framework-for-robust-speech-emotion","title":"Two-stage Framework for Robust Speech Emotion Recognition Using Target Speaker Extraction in Human Speech Noise Conditions","date":"2024-09-29","arxiv_id":"2409.19585","repositories_listed":0,"syntology":null},{"url":null,"slug":"overview-of-speaker-modeling-and-its","title":"Overview of Speaker Modeling and Its Applications: From the Lens of Deep Speaker Representation Learning","date":"2024-07-21","arxiv_id":"2407.15188","repositories_listed":0,"syntology":null},{"url":null,"slug":"speakerbeam-ss-real-time-target-speaker","title":"SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling","date":"2024-07-01","arxiv_id":"2407.01857","repositories_listed":0,"syntology":null},{"url":null,"slug":"binaural-selective-attention-model-for-target","title":"Binaural Selective Attention Model for Target Speaker Extraction","date":"2024-06-18","arxiv_id":"2406.12236","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-speaker-extraction-with-curriculum","title":"Target Speaker Extraction with Curriculum Learning","date":"2024-06-12","arxiv_id":"2406.07845","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-real-world-active-speaker-detection","title":"Enhancing Real-World Active Speaker Detection with Multi-Modal Extraction Pre-Training","date":"2024-04-01","arxiv_id":"2404.00861","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-speaker-extraction-by-directly","title":"Target Speaker Extraction by Directly Exploiting Contextual Information in the Time-Frequency Domain","date":"2024-02-27","arxiv_id":"2402.17146","repositories_listed":0,"syntology":null},{"url":null,"slug":"listening-to-multi-talker-conversations","title":"Listening to Multi-talker Conversations: Modular and End-to-end Perspectives","date":"2024-02-14","arxiv_id":"2402.08932","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-single-speech-enhancement-model-unifying","title":"A Single Speech Enhancement Model Unifying Dereverberation, Denoising, Speaker Counting, Separation, and Extraction","date":"2023-10-12","arxiv_id":"2310.08277","repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-diffusion-model-for-target","title":"Conditional Diffusion Model for Target Speaker Extraction","date":"2023-10-07","arxiv_id":"2310.04791","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-multimodal-information-based-speech-1","title":"The Multimodal Information Based Speech Processing (MISP) 2023 Challenge: Audio-Visual Target Speaker Extraction","date":"2023-09-15","arxiv_id":"2309.08348","repositories_listed":0,"syntology":null},{"url":null,"slug":"speechx-neural-codec-language-model-as-a","title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer","date":"2023-08-14","arxiv_id":"2308.06873","repositories_listed":0,"syntology":null},{"url":null,"slug":"beamformer-guided-target-speaker-extraction","title":"Beamformer-Guided Target Speaker Extraction","date":"2023-03-15","arxiv_id":"2303.08702","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-channel-target-speaker-extraction-with","title":"Multi-Channel Target Speaker Extraction with Refinement: The WavLab Submission to the Second Clarity Enhancement Challenge","date":"2023-02-15","arxiv_id":"2302.07928","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-target-speaker-extraction-with","title":"Improving Target Speaker Extraction with Sparse LDA-transformed Speaker Embeddings","date":"2023-01-16","arxiv_id":"2301.06277","repositories_listed":0,"syntology":null},{"url":null,"slug":"exarn-self-attending-rnn-for-target-speaker","title":"ExARN: self-attending RNN for target speaker extraction","date":"2022-12-02","arxiv_id":"2212.01106","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-self-supervised-models-to-multi","title":"Adapting self-supervised models to multi-talker speech recognition using speaker embeddings","date":"2022-11-01","arxiv_id":"2211.00482","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-spatial-information-with-the","title":"Exploiting spatial information with the informed complex-valued spatial autoencoder for target speaker extraction","date":"2022-10-27","arxiv_id":"2210.15512","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-time-domain-target-speaker","title":"Semi-supervised Time Domain Target Speaker Extraction with Attention","date":"2022-06-18","arxiv_id":"2206.09072","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-conditioning-single-channel-target","title":"Speaker-conditioning Single-channel Target Speaker Extraction using Conformer-based Architectures","date":"2022-05-27","arxiv_id":"2205.13851","repositories_listed":0,"syntology":null},{"url":null,"slug":"coarse-to-fine-recursive-speech-separation","title":"Coarse-to-Fine Recursive Speech Separation for Unknown Number of Speakers","date":"2022-03-30","arxiv_id":"2203.16054","repositories_listed":0,"syntology":null},{"url":null,"slug":"new-insights-on-target-speaker-extraction","title":"New Insights on Target Speaker Extraction","date":"2022-02-01","arxiv_id":"2202.00733","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-conditioned-target-speaker-extraction","title":"Speaker-conditioned Target Speaker Extraction based on Customized LSTM Cells","date":"2021-04-09","arxiv_id":"2104.04234","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-attention-fusion-for-target","title":"Multimodal Attention Fusion for Target Speaker Extraction","date":"2021-02-02","arxiv_id":"2102.01326","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-talker-mvdr-beamforming-based-on","title":"Multi-Talker MVDR Beamforming Based on Extended Complex Gaussian Mixture Model","date":"2019-10-17","arxiv_id":"1910.07753","repositories_listed":0,"syntology":null}],"syntology_records":3,"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":2,"papers_where_code_ran_first_page":"/task/target-speaker-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/target-speaker-extraction/papers/ran/1","json":"/task/target-speaker-extraction/papers/ran/1.json","rows":2}],"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":"d4189091ec4e7d7112dc196824097512c8bebc8a99a5c270da1ea93074fdaee4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}