{"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":"/dataset/wsj0-2mix-1","name":"WSJ0-2mix","full_name":null,"description_markdown":"**WSJ0-2mix** is a speech recognition corpus of speech mixtures using utterances from the Wall Street Journal (WSJ0) corpus.\r\n\r\nSource: [Deep clustering: Discriminative embeddings for segmentation and separation](/paper/deep-clustering-discriminative-embeddings-for)","description_withheld":null,"homepage":"https://www.merl.com/demos/deep-clustering","introduced_date":"2015-08-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/deep-clustering-discriminative-embeddings-for","title":"Deep clustering: Discriminative embeddings for segmentation and separation","first_author":"John R. Hershey","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Separation","url":"/task/speech-separation","datasets_with_task":"/datasets/task/speech-separation"},{"name":"Audio Source Separation","url":"/task/audio-source-separation","datasets_with_task":"/datasets/task/audio-source-separation"},{"name":"Adversarial Attack","url":"/task/adversarial-attack","datasets_with_task":"/datasets/task/adversarial-attack"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WSJ0-2mix","WSJ0-2mix-16k"],"data_loaders":[{"repo":"https://github.com/JusperLee/Conv-TasNet","url":"https://github.com/JusperLee/Conv-TasNet","frameworks":["pytorch"]}],"num_papers_in_archive":159,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-separation-on-wsj0-2mix","task":"Speech Separation","dataset_variant":"WSJ0-2mix","rows":40,"metrics":["SI-SDRi","SDRi","Number of parameters (M)","MACs (G)"],"first_row_in_archive_order":{"model":"TF-Locoformer (L) + DM","paper":"/paper/tf-locoformer-transformer-with-local-modeling","metrics":{"Number of parameters (M)":"22.5","SDRi":"25.2","SI-SDRi":"25.1"},"code_links":[{"title":"merlresearch/tf-locoformer","url":"https://github.com/merlresearch/tf-locoformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/adversarial-attack-on-wsj0-2mix","task":"Adversarial Attack","dataset_variant":"WSJ0-2mix","rows":1,"metrics":["SDR"],"first_row_in_archive_order":{"model":"ConvTasnet and Dual Path Transformers","paper":"/paper/harmonicity-plays-a-critical-role-in-dnn","metrics":{"SDR":"0.70dB"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-separation-on-wsj0-2mix-16k","task":"Speech Separation","dataset_variant":"WSJ0-2mix-16k","rows":1,"metrics":["SI-SDRi"],"first_row_in_archive_order":{"model":"MossFormer2","paper":"/paper/mossformer-pushing-the-performance-limit-of","metrics":{"SI-SDRi":"20.5"},"code_links":[{"title":"modelscope/ClearerVoice-Studio","url":"https://github.com/modelscope/ClearerVoice-Studio"},{"title":"alibabasglab/mossformer","url":"https://github.com/alibabasglab/mossformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":31,"of":31,"counts":{"papers_with_a_benchmark_row":31,"with_a_code_link":26,"where_syntology_ran_a_sample":10,"not_listed_spam_title":0,"listed":31,"listed_where_code_ran":10,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":3,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/sepmamba-state-space-models-for-speaker","slug":"sepmamba-state-space-models-for-speaker","title":"SepMamba: State-space models for speaker separation using Mamba","date":"2024-10-28","arxiv_id":"2410.20997","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/tf-locoformer-transformer-with-local-modeling","slug":"tf-locoformer-transformer-with-local-modeling","title":"TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement","date":"2024-08-06","arxiv_id":"2408.03440","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/separate-and-reconstruct-asymmetric-encoder","slug":"separate-and-reconstruct-asymmetric-encoder","title":"Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation","date":"2024-06-10","arxiv_id":"2406.05983","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/boosting-unknown-number-speaker-separation","slug":"boosting-unknown-number-speaker-separation","title":"Boosting Unknown-number Speaker Separation with Transformer Decoder-based Attractor","date":"2024-01-23","arxiv_id":"2401.12473","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/on-time-domain-conformer-models-for-monaural","slug":"on-time-domain-conformer-models-for-monaural","title":"On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments","date":"2023-10-09","arxiv_id":"2310.06125","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/spgm-prioritizing-local-features-for-enhanced","slug":"spgm-prioritizing-local-features-for-enhanced","title":"SPGM: Prioritizing Local Features for enhanced speech separation performance","date":"2023-09-22","arxiv_id":"2309.12608","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/mossformer-pushing-the-performance-limit-of","slug":"mossformer-pushing-the-performance-limit-of","title":"MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions","date":"2023-02-23","arxiv_id":"2302.11824","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["modelscope/ClearerVoice-Studio"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mossformer-pushing-the-performance-limit-of#ran","syntology_url":"https://syntology.ai/paper/2302.11824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11824"}}}},{"paper":"/paper/separate-and-diffuse-using-a-pretrained","slug":"separate-and-diffuse-using-a-pretrained","title":"Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation","date":"2023-01-25","arxiv_id":"2301.10752","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deformable-temporal-convolutional-networks","slug":"deformable-temporal-convolutional-networks","title":"Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation","date":"2022-10-27","arxiv_id":"2210.15305","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/sepit-approaching-a-single-channel-speech","slug":"sepit-approaching-a-single-channel-speech","title":"SepIt: Approaching a Single Channel Speech Separation Bound","date":"2022-05-24","arxiv_id":"2205.11801","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/harmonicity-plays-a-critical-role-in-dnn","slug":"harmonicity-plays-a-critical-role-in-dnn","title":"Harmonicity Plays a Critical Role in DNN Based Versus in Biologically-Inspired Monaural Speech Segregation Systems","date":"2022-03-08","arxiv_id":"2203.04420","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/compute-and-memory-efficient-universal-sound","slug":"compute-and-memory-efficient-universal-sound","title":"Compute and memory efficient universal sound source separation","date":"2021-03-03","arxiv_id":"2103.02644","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/sandglasset-a-light-multi-granularity-self","slug":"sandglasset-a-light-multi-granularity-self","title":"Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation","date":"2021-03-01","arxiv_id":"2103.00819","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sandglasset-a-light-multi-granularity-self#ran","syntology_url":"https://syntology.ai/paper/2103.00819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00819"}}}},{"paper":"/paper/effective-low-cost-time-domain-audio","slug":"effective-low-cost-time-domain-audio","title":"Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks","date":"2021-01-13","arxiv_id":"2101.05014","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/effective-low-cost-time-domain-audio#ran","syntology_url":"https://syntology.ai/paper/2101.05014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.05014"}}}},{"paper":"/paper/self-supervised-pre-training-reduces-label","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/attention-is-all-you-need-in-speech","slug":"attention-is-all-you-need-in-speech","title":"Attention is All You Need in Speech Separation","date":"2020-10-25","arxiv_id":"2010.13154","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/sudo-rm-rf-efficient-networks-for-universal","slug":"sudo-rm-rf-efficient-networks-for-universal","title":"Sudo rm -rf: Efficient Networks for Universal Audio Source Separation","date":"2020-07-14","arxiv_id":"2007.06833","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["etzinis/sudo_rm_rf"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sudo-rm-rf-efficient-networks-for-universal#ran","syntology_url":"https://syntology.ai/paper/2007.06833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06833"}}}},{"paper":"/paper/voice-separation-with-an-unknown-number-of","slug":"voice-separation-with-an-unknown-number-of","title":"Voice Separation with an Unknown Number of Multiple Speakers","date":"2020-02-29","arxiv_id":"2003.01531","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":12,"samples_constructed":5,"samples_ran_checked":10,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":9,"official":{"repos":["facebookresearch/svoice"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/voice-separation-with-an-unknown-number-of#ran","syntology_url":"https://syntology.ai/paper/2003.01531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.01531"}}}},{"paper":"/paper/wavesplit-end-to-end-speech-separation-by","slug":"wavesplit-end-to-end-speech-separation-by","title":"Wavesplit: End-to-End Speech Separation by Speaker Clustering","date":"2020-02-20","arxiv_id":"2002.08933","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/interrupted-and-cascaded-permutation","slug":"interrupted-and-cascaded-permutation","title":"Interrupted and cascaded permutation invariant training for speech separation","date":"2019-10-28","arxiv_id":"1910.12706","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/two-step-sound-source-separation-training-on","slug":"two-step-sound-source-separation-training-on","title":"Two-Step Sound Source Separation: Training on Learned Latent Targets","date":"2019-10-22","arxiv_id":"1910.09804","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/dual-path-rnn-efficient-long-sequence","slug":"dual-path-rnn-efficient-long-sequence","title":"Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation","date":"2019-10-14","arxiv_id":"1910.06379","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":22,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dual-path-rnn-efficient-long-sequence#ran","syntology_url":"https://syntology.ai/paper/1910.06379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06379"}}}},{"paper":"/paper/divide-and-conquer-a-deep-casa-approach-to","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improved-speech-separation-with-time-and","slug":"improved-speech-separation-with-time-and","title":"Improved Speech Separation with Time-and-Frequency Cross-domain Joint Embedding and Clustering","date":"2019-04-16","arxiv_id":"1904.07845","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tasnet-surpassing-ideal-time-frequency","slug":"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","rows_on_this_dataset":1,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":36,"samples_ran":28,"samples_constructed":0,"samples_ran_checked":22,"samples_ran_instrument_failed":6,"samples_unverified":8,"pointer_only_for_licence":16,"official":{"repos":["naplab/Conv-TasNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tasnet-surpassing-ideal-time-frequency#ran","syntology_url":"https://syntology.ai/paper/1809.07454","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.07454"}}}},{"paper":"/paper/real-time-single-channel-dereverberation-and","slug":"real-time-single-channel-dereverberation-and","title":"Real-time Single-channel Dereverberation and Separation with Time-domainAudio Separation Network","date":"2018-09-02","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/alternative-objective-functions-for-deep","slug":"alternative-objective-functions-for-deep","title":"Alternative Objective Functions for Deep Clustering","date":"2018-04-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tasnet-time-domain-audio-separation-network","slug":"tasnet-time-domain-audio-separation-network","title":"TasNet: time-domain audio separation network for real-time, single-channel speech separation","date":"2017-11-01","arxiv_id":"1711.00541","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/deep-clustering-discriminative-embeddings-for","slug":"deep-clustering-discriminative-embeddings-for","title":"Deep clustering: Discriminative embeddings for segmentation and separation","date":"2015-08-18","arxiv_id":"1508.04306","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-clustering-discriminative-embeddings-for#ran","syntology_url":"https://syntology.ai/paper/1508.04306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1508.04306"}}}},{"paper":"/paper/dual-path-transformer-network-direct-context-1","slug":"dual-path-transformer-network-direct-context-1","title":"Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation","date":null,"arxiv_id":"2007.13975","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["ujscjj/DPTNet"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dual-path-transformer-network-direct-context-1#ran","syntology_url":"https://syntology.ai/paper/2007.13975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.13975"}}}},{"paper":"/paper/mossformer2-combining-transformer-and-rnn-1","slug":"mossformer2-combining-transformer-and-rnn-1","title":"MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation","date":null,"arxiv_id":"2312.11825","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["modelscope/ClearerVoice-Studio"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mossformer2-combining-transformer-and-rnn-1#ran","syntology_url":"https://syntology.ai/paper/2312.11825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11825"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/sepmamba-state-space-models-for-speaker","slug":"sepmamba-state-space-models-for-speaker","title":"SepMamba: State-space models for speaker separation using Mamba","date":"2024-10-28","arxiv_id":"2410.20997","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/tf-locoformer-transformer-with-local-modeling","slug":"tf-locoformer-transformer-with-local-modeling","title":"TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement","date":"2024-08-06","arxiv_id":"2408.03440","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/separate-and-reconstruct-asymmetric-encoder","slug":"separate-and-reconstruct-asymmetric-encoder","title":"Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation","date":"2024-06-10","arxiv_id":"2406.05983","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/boosting-unknown-number-speaker-separation","slug":"boosting-unknown-number-speaker-separation","title":"Boosting Unknown-number Speaker Separation with Transformer Decoder-based Attractor","date":"2024-01-23","arxiv_id":"2401.12473","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/on-time-domain-conformer-models-for-monaural","slug":"on-time-domain-conformer-models-for-monaural","title":"On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments","date":"2023-10-09","arxiv_id":"2310.06125","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/spgm-prioritizing-local-features-for-enhanced","slug":"spgm-prioritizing-local-features-for-enhanced","title":"SPGM: Prioritizing Local Features for enhanced speech separation performance","date":"2023-09-22","arxiv_id":"2309.12608","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/mossformer-pushing-the-performance-limit-of","slug":"mossformer-pushing-the-performance-limit-of","title":"MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions","date":"2023-02-23","arxiv_id":"2302.11824","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["modelscope/ClearerVoice-Studio"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mossformer-pushing-the-performance-limit-of#ran","syntology_url":"https://syntology.ai/paper/2302.11824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11824"}}}},{"paper":"/paper/separate-and-diffuse-using-a-pretrained","slug":"separate-and-diffuse-using-a-pretrained","title":"Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation","date":"2023-01-25","arxiv_id":"2301.10752","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deformable-temporal-convolutional-networks","slug":"deformable-temporal-convolutional-networks","title":"Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation","date":"2022-10-27","arxiv_id":"2210.15305","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/sepit-approaching-a-single-channel-speech","slug":"sepit-approaching-a-single-channel-speech","title":"SepIt: Approaching a Single Channel Speech Separation Bound","date":"2022-05-24","arxiv_id":"2205.11801","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/harmonicity-plays-a-critical-role-in-dnn","slug":"harmonicity-plays-a-critical-role-in-dnn","title":"Harmonicity Plays a Critical Role in DNN Based Versus in Biologically-Inspired Monaural Speech Segregation Systems","date":"2022-03-08","arxiv_id":"2203.04420","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/compute-and-memory-efficient-universal-sound","slug":"compute-and-memory-efficient-universal-sound","title":"Compute and memory efficient universal sound source separation","date":"2021-03-03","arxiv_id":"2103.02644","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/sandglasset-a-light-multi-granularity-self","slug":"sandglasset-a-light-multi-granularity-self","title":"Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation","date":"2021-03-01","arxiv_id":"2103.00819","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sandglasset-a-light-multi-granularity-self#ran","syntology_url":"https://syntology.ai/paper/2103.00819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.00819"}}}},{"paper":"/paper/effective-low-cost-time-domain-audio","slug":"effective-low-cost-time-domain-audio","title":"Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks","date":"2021-01-13","arxiv_id":"2101.05014","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/effective-low-cost-time-domain-audio#ran","syntology_url":"https://syntology.ai/paper/2101.05014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.05014"}}}},{"paper":"/paper/self-supervised-pre-training-reduces-label","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/attention-is-all-you-need-in-speech","slug":"attention-is-all-you-need-in-speech","title":"Attention is All You Need in Speech Separation","date":"2020-10-25","arxiv_id":"2010.13154","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/sudo-rm-rf-efficient-networks-for-universal","slug":"sudo-rm-rf-efficient-networks-for-universal","title":"Sudo rm -rf: Efficient Networks for Universal Audio Source Separation","date":"2020-07-14","arxiv_id":"2007.06833","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["etzinis/sudo_rm_rf"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sudo-rm-rf-efficient-networks-for-universal#ran","syntology_url":"https://syntology.ai/paper/2007.06833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06833"}}}},{"paper":"/paper/voice-separation-with-an-unknown-number-of","slug":"voice-separation-with-an-unknown-number-of","title":"Voice Separation with an Unknown Number of Multiple Speakers","date":"2020-02-29","arxiv_id":"2003.01531","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":12,"samples_constructed":5,"samples_ran_checked":10,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":9,"official":{"repos":["facebookresearch/svoice"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/voice-separation-with-an-unknown-number-of#ran","syntology_url":"https://syntology.ai/paper/2003.01531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.01531"}}}},{"paper":"/paper/wavesplit-end-to-end-speech-separation-by","slug":"wavesplit-end-to-end-speech-separation-by","title":"Wavesplit: End-to-End Speech Separation by Speaker Clustering","date":"2020-02-20","arxiv_id":"2002.08933","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/interrupted-and-cascaded-permutation","slug":"interrupted-and-cascaded-permutation","title":"Interrupted and cascaded permutation invariant training for speech separation","date":"2019-10-28","arxiv_id":"1910.12706","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/two-step-sound-source-separation-training-on","slug":"two-step-sound-source-separation-training-on","title":"Two-Step Sound Source Separation: Training on Learned Latent Targets","date":"2019-10-22","arxiv_id":"1910.09804","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/dual-path-rnn-efficient-long-sequence","slug":"dual-path-rnn-efficient-long-sequence","title":"Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation","date":"2019-10-14","arxiv_id":"1910.06379","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":22,"samples_ran":19,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dual-path-rnn-efficient-long-sequence#ran","syntology_url":"https://syntology.ai/paper/1910.06379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06379"}}}},{"paper":"/paper/divide-and-conquer-a-deep-casa-approach-to","slug":"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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improved-speech-separation-with-time-and","slug":"improved-speech-separation-with-time-and","title":"Improved Speech Separation with Time-and-Frequency Cross-domain Joint Embedding and Clustering","date":"2019-04-16","arxiv_id":"1904.07845","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tasnet-surpassing-ideal-time-frequency","slug":"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","rows_on_this_dataset":1,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":36,"samples_ran":28,"samples_constructed":0,"samples_ran_checked":22,"samples_ran_instrument_failed":6,"samples_unverified":8,"pointer_only_for_licence":16,"official":{"repos":["naplab/Conv-TasNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tasnet-surpassing-ideal-time-frequency#ran","syntology_url":"https://syntology.ai/paper/1809.07454","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.07454"}}}},{"paper":"/paper/real-time-single-channel-dereverberation-and","slug":"real-time-single-channel-dereverberation-and","title":"Real-time Single-channel Dereverberation and Separation with Time-domainAudio Separation Network","date":"2018-09-02","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/alternative-objective-functions-for-deep","slug":"alternative-objective-functions-for-deep","title":"Alternative Objective Functions for Deep Clustering","date":"2018-04-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tasnet-time-domain-audio-separation-network","slug":"tasnet-time-domain-audio-separation-network","title":"TasNet: time-domain audio separation network for real-time, single-channel speech separation","date":"2017-11-01","arxiv_id":"1711.00541","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/deep-clustering-discriminative-embeddings-for","slug":"deep-clustering-discriminative-embeddings-for","title":"Deep clustering: Discriminative embeddings for segmentation and separation","date":"2015-08-18","arxiv_id":"1508.04306","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-clustering-discriminative-embeddings-for#ran","syntology_url":"https://syntology.ai/paper/1508.04306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1508.04306"}}}},{"paper":"/paper/dual-path-transformer-network-direct-context-1","slug":"dual-path-transformer-network-direct-context-1","title":"Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation","date":null,"arxiv_id":"2007.13975","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["ujscjj/DPTNet"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dual-path-transformer-network-direct-context-1#ran","syntology_url":"https://syntology.ai/paper/2007.13975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.13975"}}}},{"paper":"/paper/mossformer2-combining-transformer-and-rnn-1","slug":"mossformer2-combining-transformer-and-rnn-1","title":"MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation","date":null,"arxiv_id":"2312.11825","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["modelscope/ClearerVoice-Studio"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mossformer2-combining-transformer-and-rnn-1#ran","syntology_url":"https://syntology.ai/paper/2312.11825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11825"}}}}],"papers_where_code_ran":10,"papers_where_code_ran_first_page":"/dataset/wsj0-2mix-1/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/wsj0-2mix-1/papers/ran/1","json":"/dataset/wsj0-2mix-1/papers/ran/1.json","rows":10}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":10,"samples_harvested":99,"samples_ran":85,"samples_constructed":5,"samples_ran_checked":70,"samples_ran_instrument_failed":15,"samples_unverified":14,"pointer_only_for_licence":36,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":10,"papers_with_a_run_with_no_instrument_failure":7,"papers_where_every_run_was_an_instrument_failure":3,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"1253ddc6e16aa59ac6c94238ac3e5fa43a343d722a9f29b653afc13c95e29c51","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}