{"url":"/task/speaker-separation","name":"Speaker Separation","slug":"speaker-separation","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":58,"papers_with_code":13,"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":3,"subtasks":1,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/libricss","name":"LibriCSS","full_name":"","num_papers_in_archive":73},{"url":"/dataset/fsdnoisy18k","name":"FSDnoisy18k","full_name":"FSDnoisy18k","num_papers_in_archive":19},{"url":"/dataset/mc-grid-test","name":"MC_GRID","full_name":"Multi_Channel_Grid","num_papers_in_archive":1}],"subtasks":[{"url":"/task/multi-speaker-source-separation","name":"Multi-Speaker Source Separation"}],"parent_tasks":[],"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":13,"of":13,"tagged_in_all":58,"items":[{"url":"/paper/tasnet-surpassing-ideal-time-frequency","title":"Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation","date":"2018-09-20","arxiv_id":"1809.07454","repositories_listed":17,"syntology":{"n":36,"n_ran":7,"n_unverified":29,"n_pointer_only":16}},{"url":"/paper/voicefilter-targeted-voice-separation-by","title":"VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking","date":"2018-10-11","arxiv_id":"1810.04826","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/multi-microphone-complex-spectral-mapping-for","title":"Multi-microphone Complex Spectral Mapping for Utterance-wise and Continuous Speech Separation","date":"2020-10-04","arxiv_id":"2010.01703","repositories_listed":2,"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/single-channel-multi-speaker-separation-using","title":"Single-Channel Multi-Speaker Separation using Deep Clustering","date":"2016-07-07","arxiv_id":"1607.02173","repositories_listed":2,"syntology":null},{"url":"/paper/sepmamba-state-space-models-for-speaker","title":"SepMamba: State-space models for speaker separation using Mamba","date":"2024-10-28","arxiv_id":"2410.20997","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/blind-speech-separation-and-dereverberation","title":"Blind Speech Separation and Dereverberation using Neural Beamforming","date":"2021-03-24","arxiv_id":"2103.13443","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-pre-training-reduces-label","title":"Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training","date":"2020-10-29","arxiv_id":"2010.15366","repositories_listed":1,"syntology":null},{"url":"/paper/speech-separation-based-on-multi-stage","title":"Speech Separation Based on Multi-Stage Elaborated Dual-Path Deep BiLSTM with Auxiliary Identity Loss","date":"2020-08-06","arxiv_id":"2008.03149","repositories_listed":1,"syntology":null},{"url":"/paper/divide-and-conquer-a-deep-casa-approach-to","title":"Divide and Conquer: A Deep CASA Approach to Talker-independent Monaural Speaker Separation","date":"2019-04-25","arxiv_id":"1904.11148","repositories_listed":1,"syntology":null},{"url":"/paper/neural-separation-of-observed-and-unobserved","title":"Neural separation of observed and unobserved distributions","date":"2018-11-30","arxiv_id":"1811.12739","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/monaural-audio-speaker-separation-with-source","title":"Monaural Audio Speaker Separation with Source Contrastive Estimation","date":"2017-05-12","arxiv_id":"1705.04662","repositories_listed":1,"syntology":null},{"url":"/paper/deep-attractor-network-for-single-microphone","title":"Deep attractor network for single-microphone speaker separation","date":"2016-11-27","arxiv_id":"1611.08930","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}],"syntology_records":5,"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"}}