{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":20,"of":20,"tagged_in_all":55,"items":[{"url":"/paper/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","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_unverified":11,"n_pointer_only":41}},{"url":"/paper/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","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","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","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","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","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","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","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","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","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","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","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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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","title":"Muse: Multi-modal target speaker extraction with visual cues","date":"2020-10-15","arxiv_id":"2010.07775","repositories_listed":1,"syntology":null}],"syntology_records":2,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}