{"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 (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":10,"of":10,"tagged_in_all":48,"items":[{"url":"/paper/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","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","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","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_unverified":1,"n_pointer_only":2}},{"url":"/paper/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","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","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","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","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","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}],"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"},"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"}}