{"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/speech-enhancement","name":"Speech Enhancement","slug":"speech-enhancement","description_markdown":"**Speech Enhancement** is a signal processing task that involves improving the quality of speech signals captured under noisy or degraded conditions. The goal of speech enhancement is to make speech signals clearer, more intelligible, and more pleasant to listen to, which can be used for various applications such as voice recognition, teleconferencing, and hearing aids. A representative Github project with online demo : [ClearerVoice-Studio](https://github.com/modelscope/ClearerVoice-Studio).\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [A Fully Convolutional Neural Network For Speech Enhancement](https://arxiv.org/pdf/1609.07132v1.pdf) )</span>","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":"archive_url"},"counts":{"papers_tagged":982,"papers_with_code":280,"benchmarks":17,"benchmark_tables_in_archive":18,"benchmark_tables_shown":18,"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":24,"subtasks":4,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/speech-enhancement-on-demand","slug":"speech-enhancement-on-demand","dataset":"VoiceBank + DEMAND","dataset_url":"/dataset/demand","rows_in_archive":42,"metrics":["PESQ (wb)","CBAK","COVL","CSIG","STOI","ESTOI","SSNR","SI-SDR","Para. (M)"],"first_row_in_archive_order":{"model":"ROSE-CD(PESQ)","paper_title":"Robust One-step Speech Enhancement via Consistency Distillation","paper_url":"/paper/robust-one-step-speech-enhancement-via-1","paper_date":"2025-07-08","arxiv_id":"2507.05688","code_links":[{"title":"LiangXu123/Robust-One-step-Speech-Enhancement-via-Consistency-Distillation-ROSE-CD-","url":"https://github.com/LiangXu123/Robust-One-step-Speech-Enhancement-via-Consistency-Distillation-ROSE-CD-"}],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-deep-noise-suppression","slug":"speech-enhancement-on-deep-noise-suppression","dataset":"Deep Noise Suppression (DNS) Challenge","dataset_url":"/dataset/deep-noise-suppression-2020","rows_in_archive":36,"metrics":["PESQ-WB","SI-SDR-WB","STOI","PESQ-NB","SI-SDR-NB","Number of parameters (M)","FLOPS (G)","ESTOI","SSNR"],"first_row_in_archive_order":{"model":"ZipEnhancer (M)","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-chime-3","slug":"speech-enhancement-on-chime-3","dataset":"CHiME-3","dataset_url":null,"rows_in_archive":6,"metrics":["SDR","PESQ","ΔPESQ","STOI"],"first_row_in_archive_order":{"model":"Inter-Channel Conv-TasNet","paper_title":"Inter-channel Conv-TasNet for multichannel speech enhancement","paper_url":"/paper/inter-channel-conv-tasnet-for-multichannel","paper_date":"2021-11-08","arxiv_id":"2111.04312","code_links":[],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-ears-wham","slug":"speech-enhancement-on-ears-wham","dataset":"EARS-WHAM","dataset_url":"/dataset/ears-wham","rows_in_archive":6,"metrics":["PESQ-WB","SI-SDR","ESTOI","SIGMOS","DNSMOS","POLQA"],"first_row_in_archive_order":{"model":"Schrödinger Bridge (PESQ loss)","paper_title":"Investigating Training Objectives for Generative Speech Enhancement","paper_url":"/paper/investigating-training-objectives-for","paper_date":"2024-09-16","arxiv_id":"2409.10753","code_links":[{"title":"sp-uhh/sgmse","url":"https://github.com/sp-uhh/sgmse"}],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-easycom","slug":"speech-enhancement-on-easycom","dataset":"EasyCom","dataset_url":"/dataset/easycom","rows_in_archive":6,"metrics":["PESQ","STOI","ViSQOL","HASQI","Audio Quality MOS","SDR","ESTOI","HASPI","SI-SDR","SIIB","SNR","SegSNR"],"first_row_in_archive_order":{"model":"MaxDI (Baseline)","paper_title":"EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments","paper_url":"/paper/easycom-an-augmented-reality-dataset-to","paper_date":"2021-07-09","arxiv_id":"2107.04174","code_links":[{"title":"facebookresearch/EasyComDataset","url":"https://github.com/facebookresearch/EasyComDataset"}],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-interspeech-2020-deep","slug":"speech-enhancement-on-interspeech-2020-deep","dataset":"DNS Challenge","dataset_url":"/dataset/deep-noise-suppression-2020","rows_in_archive":5,"metrics":["PESQ-NB","PESQ-WB"],"first_row_in_archive_order":{"model":"ZipEnhancer\n(M)","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-vb-demandex","slug":"speech-enhancement-on-vb-demandex","dataset":"VB-DemandEx","dataset_url":"/dataset/vb-demandex","rows_in_archive":4,"metrics":["ESTOI","Number of parameters (M)","PESQ (wb)","SI-SDR","SSNR"],"first_row_in_archive_order":{"model":"MambAttention","paper_title":"MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement","paper_url":"/paper/mambattention-mamba-with-multi-head-attention","paper_date":"2025-07-01","arxiv_id":"2507.00966","code_links":[{"title":"nikolaikyhne/xlstm-senet","url":"https://github.com/nikolaikyhne/xlstm-senet"},{"title":"NikolaiKyhne/MambAttention","url":"https://github.com/NikolaiKyhne/MambAttention"}],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-whamr","slug":"speech-enhancement-on-whamr","dataset":"WHAMR!","dataset_url":"/dataset/whamr","rows_in_archive":4,"metrics":["PESQ","SI-SDR","ΔPESQ","SI-SNR","SDR"],"first_row_in_archive_order":{"model":"SepFormer","paper_title":"Exploring Self-Attention Mechanisms for Speech Separation","paper_url":"/paper/on-using-transformers-for-speech-separation","paper_date":"2022-02-06","arxiv_id":"2202.02884","code_links":[{"title":"speechbrain/speechbrain","url":"https://github.com/speechbrain/speechbrain"}],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-wsj0-demand-rnnoise","slug":"speech-enhancement-on-wsj0-demand-rnnoise","dataset":"WSJ0 + DEMAND + RNNoise","dataset_url":null,"rows_in_archive":3,"metrics":["PESQ-NB"],"first_row_in_archive_order":{"model":"DCUNet-MC","paper_title":"Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency Losses","paper_url":"/paper/monaural-speech-enhancement-with-complex","paper_date":"2021-02-03","arxiv_id":"2102.01993","code_links":[{"title":"modelscope/ClearerVoice-Studio","url":"https://github.com/modelscope/ClearerVoice-Studio"},{"title":"alibabasglab/frcrn","url":"https://github.com/alibabasglab/frcrn"}],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-realman","slug":"speech-enhancement-on-realman","dataset":"RealMAN","dataset_url":"/dataset/realman","rows_in_archive":2,"metrics":["DNSMOS","DNSMOS BAK","DNSMOS OVRL","DNSMOS SIG","PESQ-WB"],"first_row_in_archive_order":{"model":"CleanMel-L-map","paper_title":"CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR","paper_url":"/paper/cleanmel-mel-spectrogram-enhancement-for","paper_date":"2025-02-27","arxiv_id":"2502.20040","code_links":[{"title":"Audio-WestlakeU/CleanMel","url":"https://github.com/Audio-WestlakeU/CleanMel"}],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-voicebank-demand-2","slug":"speech-enhancement-on-voicebank-demand-2","dataset":"VoiceBank+DEMAND","dataset_url":"/dataset/voice-bank-demand","rows_in_archive":2,"metrics":["PESQ","DNSMOS","DNSMOS BAK","DNSMOS OVRL","DNSMOS SIG","ESTOI","SI-SDR","PESQ (wb)"],"first_row_in_archive_order":{"model":"ROSE-CD","paper_title":"Robust One-step Speech Enhancement via Consistency Distillation","paper_url":"/paper/robust-one-step-speech-enhancement-via-1","paper_date":"2025-07-08","arxiv_id":"2507.05688","code_links":[{"title":"LiangXu123/Robust-One-step-Speech-Enhancement-via-Consistency-Distillation-ROSE-CD-","url":"https://github.com/LiangXu123/Robust-One-step-Speech-Enhancement-via-Consistency-Distillation-ROSE-CD-"}],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-demand-1","slug":"speech-enhancement-on-demand-1","dataset":"DEMAND","dataset_url":null,"rows_in_archive":1,"metrics":["CBAK","COVL","CSIG","PESQ"],"first_row_in_archive_order":{"model":"Wave-U-Net","paper_title":"Improved Speech Enhancement with the Wave-U-Net","paper_url":"/paper/improved-speech-enhancement-with-the-wave-u","paper_date":"2018-11-27","arxiv_id":"1811.11307","code_links":[{"title":"craigmacartney/Wave-U-Net-For-Speech-Enhancement","url":"https://github.com/craigmacartney/Wave-U-Net-For-Speech-Enhancement"},{"title":"pheepa/DCUnet","url":"https://github.com/pheepa/DCUnet"},{"title":"MattSegal/speech-enhancement","url":"https://github.com/MattSegal/speech-enhancement"}],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-grid-corpus-mixed","slug":"speech-enhancement-on-grid-corpus-mixed","dataset":"GRID corpus (mixed-speech)","dataset_url":"/dataset/grid","rows_in_archive":1,"metrics":["PESQ"],"first_row_in_archive_order":{"model":"Audio-Visual concat-ref","paper_title":"Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments","paper_url":"/paper/face-landmark-based-speaker-independent-audio","paper_date":"2018-11-06","arxiv_id":"1811.02480","code_links":[{"title":"dr-pato/audio_visual_speech_enhancement","url":"https://github.com/dr-pato/audio_visual_speech_enhancement"}],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-librispeech","slug":"speech-enhancement-on-librispeech","dataset":"LibriSpeechDuplicate","dataset_url":null,"rows_in_archive":1,"metrics":["Audio Quality MOS"],"first_row_in_archive_order":{"model":"SE-MelGAN","paper_title":"SE-MelGAN -- Speaker Agnostic Rapid Speech Enhancement","paper_url":"/paper/se-melgan-speaker-agnostic-rapid-speech","paper_date":"2020-06-13","arxiv_id":"2006.07637","code_links":[],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-spatialized-dns","slug":"speech-enhancement-on-spatialized-dns","dataset":"spatialized DNS challenge","dataset_url":null,"rows_in_archive":1,"metrics":["PESQ","SI-SDR","STOI"],"first_row_in_archive_order":{"model":"DeFT-AN","paper_title":"DeFT-AN: Dense Frequency-Time Attentive Network for Multichannel Speech Enhancement","paper_url":"/paper/deft-an-dense-frequency-time-attentive","paper_date":"2022-12-15","arxiv_id":"2212.07570","code_links":[{"title":"donghoney0416/DeFT-AN","url":"https://github.com/donghoney0416/DeFT-AN"}],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-tcd-timit-corpus-mixed","slug":"speech-enhancement-on-tcd-timit-corpus-mixed","dataset":"TCD-TIMIT corpus (mixed-speech)","dataset_url":"/dataset/timit","rows_in_archive":1,"metrics":["PESQ"],"first_row_in_archive_order":{"model":"Audio-Visual concat-ref","paper_title":"Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments","paper_url":"/paper/face-landmark-based-speaker-independent-audio","paper_date":"2018-11-06","arxiv_id":"1811.02480","code_links":[{"title":"dr-pato/audio_visual_speech_enhancement","url":"https://github.com/dr-pato/audio_visual_speech_enhancement"}],"syntology":null}},{"leaderboard":"/sota/speech-enhancement-on-wham","slug":"speech-enhancement-on-wham","dataset":"WHAM!","dataset_url":"/dataset/wham","rows_in_archive":1,"metrics":["PESQ","SDR","SI-SNR"],"first_row_in_archive_order":{"model":"SepFormer","paper_title":"Exploring Self-Attention Mechanisms for Speech Separation","paper_url":"/paper/on-using-transformers-for-speech-separation","paper_date":"2022-02-06","arxiv_id":"2202.02884","code_links":[{"title":"speechbrain/speechbrain","url":"https://github.com/speechbrain/speechbrain"}],"syntology":null}},{"leaderboard":null,"slug":"speech-enhancement-on-dns-4","dataset":"DNS-4","dataset_url":null,"rows_in_archive":0,"metrics":["DNSMOS BAK","DNSMOS OVRL","DNSMOS SIG"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/librimix","name":"LibriMix","full_name":"","num_papers_in_archive":122},{"url":"/dataset/wham","name":"WHAM!","full_name":"WSJ0 Hipster Ambient Mixtures","num_papers_in_archive":114},{"url":"/dataset/ava","name":"AVA","full_name":"Atomic Visual Actions","num_papers_in_archive":113},{"url":"/dataset/whamr","name":"WHAMR!","full_name":"WHAM! with synthetic reverberated sources","num_papers_in_archive":57},{"url":"/dataset/reverb-challenge","name":"ReVerb Challenge","full_name":"REverberant Voice Enhancement and Recognition Benchmark","num_papers_in_archive":55},{"url":"/dataset/demand","name":"VoiceBank + DEMAND","full_name":"Noisy speech database for training speech enhancement algorithms and TTS models","num_papers_in_archive":53},{"url":"/dataset/deep-noise-suppression-2020","name":"DNS Challenge","full_name":"Deep Noise Suppression Challenge","num_papers_in_archive":48},{"url":"/dataset/chime-5","name":"CHiME-5","full_name":"CHiME Speech Separation and Recognition Challenge","num_papers_in_archive":42},{"url":"/dataset/timit","name":"TIMIT","full_name":"TIMIT Acoustic-Phonetic Continuous Speech Corpus","num_papers_in_archive":31},{"url":"/dataset/ava-activespeaker","name":"AVA-ActiveSpeaker","full_name":"","num_papers_in_archive":22},{"url":"/dataset/easycom","name":"EasyCom","full_name":"","num_papers_in_archive":22},{"url":"/dataset/voice-bank-demand","name":"VoiceBank+DEMAND","full_name":"","num_papers_in_archive":16},{"url":"/dataset/l3das22","name":"L3DAS22","full_name":"","num_papers_in_archive":13},{"url":"/dataset/ears-wham","name":"EARS-WHAM","full_name":"","num_papers_in_archive":11},{"url":"/dataset/grid","name":"GRID Dataset","full_name":"","num_papers_in_archive":10},{"url":"/dataset/l3das21","name":"L3DAS21","full_name":"","num_papers_in_archive":6},{"url":"/dataset/realman","name":"RealMAN","full_name":"A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization","num_papers_in_archive":5},{"url":"/dataset/cas-vsr-s101","name":"CAS-VSR-S101","full_name":"","num_papers_in_archive":1},{"url":"/dataset/gneutralspeech-female","name":"GneutralSpeech Female","full_name":"","num_papers_in_archive":1},{"url":"/dataset/gneutralspeech-male","name":"GneutralSpeech Male","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mdrt","name":"mDRT","full_name":"Multilingual Diagnostic Rhyme Test","num_papers_in_archive":1},{"url":"/dataset/nisqa-speech-quality-corpus","name":"NISQA Speech Quality Corpus","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vb-demandex","name":"VB-DemandEx","full_name":"","num_papers_in_archive":1},{"url":"/dataset/whamr-ext","name":"WHAMR_ext","full_name":"WHAMR_ext","num_papers_in_archive":1}],"subtasks":[{"url":"/task/bandwidth-extension","name":"Bandwidth Extension"},{"url":"/task/packet-loss-concealment","name":"Packet Loss Concealment"},{"url":"/task/speech-dereverberation","name":"Speech Dereverberation"},{"url":"/task/speech-intelligibility-evaluation","name":"Speech Intelligibility Evaluation"}],"parent_tasks":[],"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":10,"rows_per_page":100,"shown":100,"of":982,"of_with_code":280,"tagged_in_all":982,"counts":{"archive_papers_tagged":982,"with_a_code_link":280,"where_syntology_ran_a_sample":54,"not_listed_spam_title":0,"listed":982,"listed_where_code_ran":54,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":45,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":45,"listed_every_run_a_failure_of_syntologys_instrument":9,"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/proximal-policy-optimization-algorithms","slug":"proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","arxiv_id":"1707.06347","repositories_listed":188,"syntology":{"n":176,"n_ran":99,"n_constructed":53,"n_ran_checked":71,"n_instrument":28,"n_unverified":77,"n_honours":7,"n_violates":2,"n_no_contract":62,"n_pointer_only":94,"phrase":"99 ran (of which 53 constructed an object rather than computing a result; 71 with no instrument failure: 7 honoured, 2 violated, 62 with no contract checked; 28 where Syntology's instrument failed) · 77 unverified","sample_list":"/paper/proximal-policy-optimization-algorithms#ran","syntology_url":"https://syntology.ai/paper/1707.06347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.06347"}},"official":null}},{"url":"/paper/perceptual-losses-for-real-time-style","slug":"perceptual-losses-for-real-time-style","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","date":"2016-03-27","arxiv_id":"1603.08155","repositories_listed":80,"syntology":{"n":46,"n_ran":34,"n_constructed":0,"n_ran_checked":26,"n_instrument":8,"n_unverified":12,"n_honours":2,"n_violates":2,"n_no_contract":22,"n_pointer_only":9,"phrase":"34 ran (of which 0 constructed an object rather than computing a result; 26 with no instrument failure: 2 honoured, 2 violated, 22 with no contract checked; 8 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/perceptual-losses-for-real-time-style#ran","syntology_url":"https://syntology.ai/paper/1603.08155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.08155"}},"official":null}},{"url":"/paper/segan-speech-enhancement-generative","slug":"segan-speech-enhancement-generative","title":"SEGAN: Speech Enhancement Generative Adversarial Network","date":"2017-03-28","arxiv_id":"1703.09452","repositories_listed":21,"syntology":{"n":39,"n_ran":26,"n_constructed":0,"n_ran_checked":23,"n_instrument":3,"n_unverified":13,"n_honours":0,"n_violates":0,"n_no_contract":23,"n_pointer_only":6,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 3 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/segan-speech-enhancement-generative#ran","syntology_url":"https://syntology.ai/paper/1703.09452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.09452"}},"official":{"repos":["santi-pdp/segan"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/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","repositories_listed":17,"syntology":{"n":36,"n_ran":28,"n_constructed":0,"n_ran_checked":22,"n_instrument":6,"n_unverified":8,"n_honours":3,"n_violates":2,"n_no_contract":17,"n_pointer_only":16,"phrase":"28 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 3 honoured, 2 violated, 17 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified","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"}},"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"]}}},{"url":"/paper/zero-reference-deep-curve-estimation-for-low","slug":"zero-reference-deep-curve-estimation-for-low","title":"Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement","date":"2020-01-19","arxiv_id":"2001.06826","repositories_listed":13,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/zero-reference-deep-curve-estimation-for-low#ran","syntology_url":"https://syntology.ai/paper/2001.06826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.06826"}},"official":{"repos":["Li-Chongyi/Zero-DCE"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/phase-aware-speech-enhancement-with-deep-1","slug":"phase-aware-speech-enhancement-with-deep-1","title":"Phase-aware Speech Enhancement with Deep Complex U-Net","date":"2019-03-07","arxiv_id":"1903.03107","repositories_listed":9,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/phase-aware-speech-enhancement-with-deep-1#ran","syntology_url":"https://syntology.ai/paper/1903.03107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.03107"}},"official":null}},{"url":"/paper/speecht5-unified-modal-encoder-decoder-pre","slug":"speecht5-unified-modal-encoder-decoder-pre","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","date":"2021-10-14","arxiv_id":"2110.07205","repositories_listed":6,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/speecht5-unified-modal-encoder-decoder-pre#ran","syntology_url":"https://syntology.ai/paper/2110.07205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.07205"}},"official":{"repos":["microsoft/speecht5"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/soundstream-an-end-to-end-neural-audio-codec","slug":"soundstream-an-end-to-end-neural-audio-codec","title":"SoundStream: An End-to-End Neural Audio Codec","date":"2021-07-07","arxiv_id":"2107.03312","repositories_listed":6,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/soundstream-an-end-to-end-neural-audio-codec#ran","syntology_url":"https://syntology.ai/paper/2107.03312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.03312"}},"official":null}},{"url":"/paper/fullsubnet-a-full-band-and-sub-band-fusion","slug":"fullsubnet-a-full-band-and-sub-band-fusion","title":"FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement","date":"2020-10-29","arxiv_id":"2010.15508","repositories_listed":6,"syntology":{"n":21,"n_ran":17,"n_constructed":0,"n_ran_checked":17,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/fullsubnet-a-full-band-and-sub-band-fusion#ran","syntology_url":"https://syntology.ai/paper/2010.15508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.15508"}},"official":null}},{"url":"/paper/a-fully-convolutional-neural-network-for","slug":"a-fully-convolutional-neural-network-for","title":"A Fully Convolutional Neural Network for Speech Enhancement","date":"2016-09-22","arxiv_id":"1609.07132","repositories_listed":6,"syntology":null},{"url":"/paper/wavecrn-an-efficient-convolutional-recurrent","slug":"wavecrn-an-efficient-convolutional-recurrent","title":"WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancement","date":"2020-04-06","arxiv_id":"2004.04098","repositories_listed":5,"syntology":null},{"url":"/paper/metricgan-generative-adversarial-networks","slug":"metricgan-generative-adversarial-networks","title":"MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement","date":"2019-05-13","arxiv_id":"1905.04874","repositories_listed":5,"syntology":null},{"url":"/paper/voicefilter-targeted-voice-separation-by","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/voicefilter-targeted-voice-separation-by#ran","syntology_url":"https://syntology.ai/paper/1810.04826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.04826"}},"official":null}},{"url":"/paper/rnnoise-ex-hybrid-speech-enhancement-system","slug":"rnnoise-ex-hybrid-speech-enhancement-system","title":"RNNoise-Ex: Hybrid Speech Enhancement System based on RNN and Spectral Features","date":"2021-05-25","arxiv_id":"2105.11813","repositories_listed":4,"syntology":null},{"url":"/paper/whispered-to-voiced-alaryngeal-speech","slug":"whispered-to-voiced-alaryngeal-speech","title":"Whispered-to-voiced Alaryngeal Speech Conversion with Generative Adversarial Networks","date":"2018-08-31","arxiv_id":"1808.10687","repositories_listed":4,"syntology":null},{"url":"/paper/hifi-a-unified-framework-for-neural-vocoding","slug":"hifi-a-unified-framework-for-neural-vocoding","title":"HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement","date":"2022-03-24","arxiv_id":"2203.13086","repositories_listed":3,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hifi-a-unified-framework-for-neural-vocoding#ran","syntology_url":"https://syntology.ai/paper/2203.13086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13086"}},"official":{"repos":["andreevp/wvmos"],"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":["listed","official"]}}},{"url":"/paper/metricgan-an-improved-version-of-metricgan","slug":"metricgan-an-improved-version-of-metricgan","title":"MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement","date":"2021-04-08","arxiv_id":"2104.03538","repositories_listed":3,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/metricgan-an-improved-version-of-metricgan#ran","syntology_url":"https://syntology.ai/paper/2104.03538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.03538"}},"official":{"repos":["speechbrain/speechbrain"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/real-time-speech-enhancement-in-the-waveform","slug":"real-time-speech-enhancement-in-the-waveform","title":"Real Time Speech Enhancement in the Waveform Domain","date":"2020-06-23","arxiv_id":"2006.12847","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/real-time-speech-enhancement-in-the-waveform#ran","syntology_url":"https://syntology.ai/paper/2006.12847","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.12847"}},"official":{"repos":["facebookresearch/denoiser"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/weighted-speech-distortion-losses-for-neural-1","slug":"weighted-speech-distortion-losses-for-neural-1","title":"Weighted Speech Distortion Losses for Neural-network-based Real-time Speech Enhancement","date":"2020-02-12","arxiv_id":"2001.10601","repositories_listed":3,"syntology":null},{"url":"/paper/spleeter-a-fast-and-state-of-the-art-music","slug":"spleeter-a-fast-and-state-of-the-art-music","title":"Spleeter: A Fast And State-of-the Art Music Source Separation Tool With Pre-trained Models","date":"2019-11-04","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/rvad-an-unsupervised-segment-based-robust","slug":"rvad-an-unsupervised-segment-based-robust","title":"rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method","date":"2019-06-09","arxiv_id":"1906.03588","repositories_listed":3,"syntology":null},{"url":"/paper/fast-multichannel-source-separation-based-on","slug":"fast-multichannel-source-separation-based-on","title":"Fast Multichannel Source Separation Based on Jointly Diagonalizable Spatial Covariance Matrices","date":"2019-03-08","arxiv_id":"1903.03237","repositories_listed":3,"syntology":null},{"url":"/paper/improved-speech-enhancement-with-the-wave-u","slug":"improved-speech-enhancement-with-the-wave-u","title":"Improved Speech Enhancement with the Wave-U-Net","date":"2018-11-27","arxiv_id":"1811.11307","repositories_listed":3,"syntology":null},{"url":"/paper/language-and-noise-transfer-in-speech","slug":"language-and-noise-transfer-in-speech","title":"Language and Noise Transfer in Speech Enhancement Generative Adversarial Network","date":"2017-12-18","arxiv_id":"1712.06340","repositories_listed":3,"syntology":null},{"url":"/paper/mambattention-mamba-with-multi-head-attention","slug":"mambattention-mamba-with-multi-head-attention","title":"MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement","date":"2025-07-01","arxiv_id":"2507.00966","repositories_listed":2,"syntology":null},{"url":"/paper/sonicsim-a-customizable-simulation-platform","slug":"sonicsim-a-customizable-simulation-platform","title":"SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios","date":"2024-10-02","arxiv_id":"2410.01481","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sonicsim-a-customizable-simulation-platform#ran","syntology_url":"https://syntology.ai/paper/2410.01481","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01481"}},"official":{"repos":["jusperlee/sonicsim"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/hold-me-tight-stable-encoder-decoder-design","slug":"hold-me-tight-stable-encoder-decoder-design","title":"Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement","date":"2024-08-30","arxiv_id":"2408.17358","repositories_listed":2,"syntology":null},{"url":"/paper/ears-an-anechoic-fullband-speech-dataset","slug":"ears-an-anechoic-fullband-speech-dataset","title":"EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation","date":"2024-06-10","arxiv_id":"2406.06185","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ears-an-anechoic-fullband-speech-dataset#ran","syntology_url":"https://syntology.ai/paper/2406.06185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06185"}},"official":{"repos":["facebookresearch/ears_dataset"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/lauragpt-listen-attend-understand-and","slug":"lauragpt-listen-attend-understand-and","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","date":"2023-10-07","arxiv_id":"2310.04673","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lauragpt-listen-attend-understand-and#ran","syntology_url":"https://syntology.ai/paper/2310.04673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04673"}},"official":null}},{"url":"/paper/multi-dimensional-speech-quality-assessment","slug":"multi-dimensional-speech-quality-assessment","title":"Multi-dimensional Speech Quality Assessment in Crowdsourcing","date":"2023-09-14","arxiv_id":"2309.07385","repositories_listed":2,"syntology":null},{"url":"/paper/a-mask-free-neural-network-for-monaural","slug":"a-mask-free-neural-network-for-monaural","title":"A Mask Free Neural Network for Monaural Speech Enhancement","date":"2023-06-07","arxiv_id":"2306.04286","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-mask-free-neural-network-for-monaural#ran","syntology_url":"https://syntology.ai/paper/2306.04286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.04286"}},"official":{"repos":["ioyy900205/mfnet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/reducing-the-prior-mismatch-of-stochastic","slug":"reducing-the-prior-mismatch-of-stochastic","title":"Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement","date":"2023-02-28","arxiv_id":"2302.14748","repositories_listed":2,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reducing-the-prior-mismatch-of-stochastic#ran","syntology_url":"https://syntology.ai/paper/2302.14748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.14748"}},"official":{"repos":["sp-uhh/sgmse-bbed"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/paaploss-a-phonetic-aligned-acoustic","slug":"paaploss-a-phonetic-aligned-acoustic","title":"PAAPLoss: A Phonetic-Aligned Acoustic Parameter Loss for Speech Enhancement","date":"2023-02-16","arxiv_id":"2302.08095","repositories_listed":2,"syntology":null},{"url":"/paper/taploss-a-temporal-acoustic-parameter-loss","slug":"taploss-a-temporal-acoustic-parameter-loss","title":"TAPLoss: A Temporal Acoustic Parameter Loss for Speech Enhancement","date":"2023-02-16","arxiv_id":"2302.08088","repositories_listed":2,"syntology":null},{"url":"/paper/storm-a-diffusion-based-stochastic","slug":"storm-a-diffusion-based-stochastic","title":"StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation","date":"2022-12-22","arxiv_id":"2212.11851","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/storm-a-diffusion-based-stochastic#ran","syntology_url":"https://syntology.ai/paper/2212.11851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.11851"}},"official":null}},{"url":"/paper/speechlmscore-evaluating-speech-generation","slug":"speechlmscore-evaluating-speech-generation","title":"SpeechLMScore: Evaluating speech generation using speech language model","date":"2022-12-08","arxiv_id":"2212.04559","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/speechlmscore-evaluating-speech-generation#ran","syntology_url":"https://syntology.ai/paper/2212.04559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04559"}},"official":{"repos":["espnet/espnet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/hybrid-transformers-for-music-source","slug":"hybrid-transformers-for-music-source","title":"Hybrid Transformers for Music Source Separation","date":"2022-11-15","arxiv_id":"2211.08553","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hybrid-transformers-for-music-source#ran","syntology_url":"https://syntology.ai/paper/2211.08553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.08553"}},"official":{"repos":["facebookresearch/demucs"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/scenefake-an-initial-dataset-and-benchmarks","slug":"scenefake-an-initial-dataset-and-benchmarks","title":"SceneFake: An Initial Dataset and Benchmarks for Scene Fake Audio Detection","date":"2022-11-11","arxiv_id":"2211.06073","repositories_listed":2,"syntology":null},{"url":"/paper/a-teacher-student-framework-for-unsupervised","slug":"a-teacher-student-framework-for-unsupervised","title":"A Training and Inference Strategy Using Noisy and Enhanced Speech as Target for Speech Enhancement without Clean Speech","date":"2022-10-27","arxiv_id":"2210.15368","repositories_listed":2,"syntology":null},{"url":"/paper/cmgan-conformer-based-metric-gan-for-monaural","slug":"cmgan-conformer-based-metric-gan-for-monaural","title":"CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement","date":"2022-09-22","arxiv_id":"2209.11112","repositories_listed":2,"syntology":null},{"url":"/paper/speech-enhancement-with-score-based","slug":"speech-enhancement-with-score-based","title":"Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain","date":"2022-03-31","arxiv_id":"2203.17004","repositories_listed":2,"syntology":null},{"url":"/paper/fullsubnet-channel-attention-fullsubnet-with","slug":"fullsubnet-channel-attention-fullsubnet-with","title":"FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement","date":"2022-03-23","arxiv_id":"2203.12188","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fullsubnet-channel-attention-fullsubnet-with#ran","syntology_url":"https://syntology.ai/paper/2203.12188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12188"}},"official":{"repos":["thuhcsi/fullsubnet-plus"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/remixit-continual-self-training-of-speech","slug":"remixit-continual-self-training-of-speech","title":"RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing","date":"2022-02-17","arxiv_id":"2202.08862","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/remixit-continual-self-training-of-speech#ran","syntology_url":"https://syntology.ai/paper/2202.08862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.08862"}},"official":{"repos":["etzinis/unsup_speech_enh_adaptation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/conditional-diffusion-probabilistic-model-for","slug":"conditional-diffusion-probabilistic-model-for","title":"Conditional Diffusion Probabilistic Model for Speech Enhancement","date":"2022-02-10","arxiv_id":"2202.05256","repositories_listed":2,"syntology":null},{"url":"/paper/bloom-net-blockwise-optimization-for-masking","slug":"bloom-net-blockwise-optimization-for-masking","title":"BLOOM-Net: Blockwise Optimization for Masking Networks Toward Scalable and Efficient Speech Enhancement","date":"2021-11-17","arxiv_id":"2111.09372","repositories_listed":2,"syntology":null},{"url":"/paper/metricgan-u-unsupervised-speech-enhancement","slug":"metricgan-u-unsupervised-speech-enhancement","title":"MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speech","date":"2021-10-12","arxiv_id":"2110.05866","repositories_listed":2,"syntology":null},{"url":"/paper/interactive-feature-fusion-for-end-to-end","slug":"interactive-feature-fusion-for-end-to-end","title":"Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition","date":"2021-10-11","arxiv_id":"2110.05267","repositories_listed":2,"syntology":null},{"url":"/paper/a-causal-u-net-based-neural-beamforming","slug":"a-causal-u-net-based-neural-beamforming","title":"A Causal U-net based Neural Beamforming Network for Real-Time Multi-Channel Speech Enhancement","date":"2021-08-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/meshrir-a-dataset-of-room-impulse-responses","slug":"meshrir-a-dataset-of-room-impulse-responses","title":"MeshRIR: A Dataset of Room Impulse Responses on Meshed Grid Points For Evaluating Sound Field Analysis and Synthesis Methods","date":"2021-06-21","arxiv_id":"2106.10801","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meshrir-a-dataset-of-room-impulse-responses#ran","syntology_url":"https://syntology.ai/paper/2106.10801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.10801"}},"official":{"repos":["sh01k/MeshRIR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dechorate-a-calibrated-room-impulse-response","slug":"dechorate-a-calibrated-room-impulse-response","title":"dEchorate: a Calibrated Room Impulse Response Database for Echo-aware Signal Processing","date":"2021-04-27","arxiv_id":"2104.13168","repositories_listed":2,"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/dechorate-a-calibrated-room-impulse-response#ran","syntology_url":"https://syntology.ai/paper/2104.13168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.13168"}},"official":{"repos":["Chutlhu/dEchorate"],"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/speech-denoising-without-clean-training-data","slug":"speech-denoising-without-clean-training-data","title":"Speech Denoising Without Clean Training Data: A Noise2Noise Approach","date":"2021-04-08","arxiv_id":"2104.03838","repositories_listed":2,"syntology":null},{"url":"/paper/monaural-speech-enhancement-with-complex","slug":"monaural-speech-enhancement-with-complex","title":"Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency Losses","date":"2021-02-03","arxiv_id":"2102.01993","repositories_listed":2,"syntology":null},{"url":"/paper/a-perceptually-motivated-approach-for-low-1","slug":"a-perceptually-motivated-approach-for-low-1","title":"A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech","date":"2020-08-27","arxiv_id":"2008.04259","repositories_listed":2,"syntology":null},{"url":"/paper/exploring-deep-hybrid-tensor-to-vector","slug":"exploring-deep-hybrid-tensor-to-vector","title":"Exploring Deep Hybrid Tensor-to-Vector Network Architectures for Regression Based Speech Enhancement","date":"2020-07-25","arxiv_id":"2007.13024","repositories_listed":2,"syntology":null},{"url":"/paper/deep-residual-dense-lattice-network-for","slug":"deep-residual-dense-lattice-network-for","title":"Deep Residual-Dense Lattice Network for Speech Enhancement","date":"2020-02-27","arxiv_id":"2002.12794","repositories_listed":2,"syntology":null},{"url":"/paper/tensor-to-vector-regression-for-multi-channel","slug":"tensor-to-vector-regression-for-multi-channel","title":"Tensor-to-Vector Regression for Multi-channel Speech Enhancement based on Tensor-Train Network","date":"2020-02-03","arxiv_id":"2002.00544","repositories_listed":2,"syntology":null},{"url":"/paper/improving-gans-for-speech-enhancement","slug":"improving-gans-for-speech-enhancement","title":"Improving GANs for Speech Enhancement","date":"2020-01-15","arxiv_id":"2001.05532","repositories_listed":2,"syntology":null},{"url":"/paper/speech-vgg-a-deep-feature-extractor-for","slug":"speech-vgg-a-deep-feature-extractor-for","title":"Word-level Embeddings for Cross-Task Transfer Learning in Speech Processing","date":"2019-10-22","arxiv_id":"1910.09909","repositories_listed":2,"syntology":null},{"url":"/paper/rhr-net-a-residual-hourglass-recurrent-neural","slug":"rhr-net-a-residual-hourglass-recurrent-neural","title":"RHR-Net: A Residual Hourglass Recurrent Neural Network for Speech Enhancement","date":"2019-04-15","arxiv_id":"1904.07294","repositories_listed":2,"syntology":null},{"url":"/paper/ava-activespeaker-an-audio-visual-dataset-for","slug":"ava-activespeaker-an-audio-visual-dataset-for","title":"AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection","date":"2019-01-05","arxiv_id":"1901.01342","repositories_listed":2,"syntology":null},{"url":"/paper/speech-denoising-convolutional-neural-network","slug":"speech-denoising-convolutional-neural-network","title":"Speech Denoising Convolutional Neural Network trained with Deep Feature Losses.","date":"2018-06-27","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/robust-one-step-speech-enhancement-via-1","slug":"robust-one-step-speech-enhancement-via-1","title":"Robust One-step Speech Enhancement via Consistency Distillation","date":"2025-07-08","arxiv_id":"2507.05688","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-speech-enhancement-via-embeddings","slug":"efficient-speech-enhancement-via-embeddings","title":"Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders","date":"2025-06-13","arxiv_id":"2506.11514","repositories_listed":1,"syntology":null},{"url":"/paper/lessons-learned-from-the-urgent-2024-speech","slug":"lessons-learned-from-the-urgent-2024-speech","title":"Lessons Learned from the URGENT 2024 Speech Enhancement Challenge","date":"2025-06-02","arxiv_id":"2506.01611","repositories_listed":1,"syntology":null},{"url":"/paper/a-lightweight-hybrid-dual-channel-speech","slug":"a-lightweight-hybrid-dual-channel-speech","title":"A Lightweight Hybrid Dual Channel Speech Enhancement System under Low-SNR Conditions","date":"2025-05-26","arxiv_id":"2505.19597","repositories_listed":1,"syntology":null},{"url":"/paper/flowse-efficient-and-high-quality-speech","slug":"flowse-efficient-and-high-quality-speech","title":"FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching","date":"2025-05-26","arxiv_id":"2505.19476","repositories_listed":1,"syntology":null},{"url":"/paper/mel-mcnet-a-mel-scale-framework-for-online","slug":"mel-mcnet-a-mel-scale-framework-for-online","title":"Mel-McNet: A Mel-Scale Framework for Online Multichannel Speech Enhancement","date":"2025-05-26","arxiv_id":"2505.19576","repositories_listed":1,"syntology":null},{"url":"/paper/training-free-multi-step-audio-source","slug":"training-free-multi-step-audio-source","title":"Training-Free Multi-Step Audio Source Separation","date":"2025-05-26","arxiv_id":"2505.19534","repositories_listed":1,"syntology":null},{"url":"/paper/cogenav-versatile-audio-visual-representation","slug":"cogenav-versatile-audio-visual-representation","title":"CoGenAV: Versatile Audio-Visual Representation Learning via Contrastive-Generative Synchronization","date":"2025-05-06","arxiv_id":"2505.03186","repositories_listed":1,"syntology":null},{"url":"/paper/hifi-stream-streaming-speech-enhancement-with","slug":"hifi-stream-streaming-speech-enhancement-with","title":"HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial Networks","date":"2025-03-21","arxiv_id":"2503.17141","repositories_listed":1,"syntology":null},{"url":"/paper/room-impulse-response-estimation-through","slug":"room-impulse-response-estimation-through","title":"Room Impulse Response Estimation through Optimal Mass Transport Barycenters","date":"2025-03-18","arxiv_id":"2503.14207","repositories_listed":1,"syntology":null},{"url":"/paper/fnse-sbgan-far-field-speech-enhancement-with","slug":"fnse-sbgan-far-field-speech-enhancement-with","title":"FNSE-SBGAN: Far-field Speech Enhancement with Schrodinger Bridge and Generative Adversarial Networks","date":"2025-03-17","arxiv_id":"2503.12936","repositories_listed":1,"syntology":null},{"url":"/paper/llase-g1-incentivizing-generalization","slug":"llase-g1-incentivizing-generalization","title":"LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement","date":"2025-03-01","arxiv_id":"2503.00493","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/llase-g1-incentivizing-generalization#ran","syntology_url":"https://syntology.ai/paper/2503.00493","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00493"}},"official":{"repos":["Kevin-naticl/LLaSE-G1"],"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":["official"]}}},{"url":"/paper/ul-unas-ultra-lightweight-u-nets-for-real","slug":"ul-unas-ultra-lightweight-u-nets-for-real","title":"UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture Search","date":"2025-03-01","arxiv_id":"2503.00340","repositories_listed":1,"syntology":null},{"url":"/paper/cleanmel-mel-spectrogram-enhancement-for","slug":"cleanmel-mel-spectrogram-enhancement-for","title":"CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR","date":"2025-02-27","arxiv_id":"2502.20040","repositories_listed":1,"syntology":null},{"url":"/paper/primek-net-multi-scale-spectral-learning-via","slug":"primek-net-multi-scale-spectral-learning-via","title":"PrimeK-Net: Multi-scale Spectral Learning via Group Prime-Kernel Convolutional Neural Networks for Single Channel Speech Enhancement","date":"2025-02-27","arxiv_id":"2502.19906","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-convolution-for-cnn-based-speech","slug":"adaptive-convolution-for-cnn-based-speech","title":"Adaptive Convolution for CNN-based Speech Enhancement Models","date":"2025-02-20","arxiv_id":"2502.14224","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/speech-enhancement-with-overlapped-frame","slug":"speech-enhancement-with-overlapped-frame","title":"Speech Enhancement with Overlapped-Frame Information Fusion and Causal Self-Attention","date":"2025-01-21","arxiv_id":"2501.12004","repositories_listed":1,"syntology":null},{"url":"/paper/sef-pnet-speaker-encoder-free-personalized","slug":"sef-pnet-speaker-encoder-free-personalized","title":"SEF-PNet: Speaker Encoder-Free Personalized Speech Enhancement with Local and Global Contexts Aggregation","date":"2025-01-20","arxiv_id":"2501.11274","repositories_listed":1,"syntology":null},{"url":"/paper/estimation-and-restoration-of-unknown","slug":"estimation-and-restoration-of-unknown","title":"Estimation and Restoration of Unknown Nonlinear Distortion using Diffusion","date":"2025-01-10","arxiv_id":"2501.05959","repositories_listed":1,"syntology":null},{"url":"/paper/xlstm-senet-xlstm-for-single-channel-speech","slug":"xlstm-senet-xlstm-for-single-channel-speech","title":"xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement","date":"2025-01-10","arxiv_id":"2501.06146","repositories_listed":1,"syntology":null},{"url":"/paper/ancogen-analysis-control-and-generation-of","slug":"ancogen-analysis-control-and-generation-of","title":"AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder","date":"2025-01-09","arxiv_id":"2501.05332","repositories_listed":1,"syntology":null},{"url":"/paper/flowhigh-towards-efficient-and-high-quality","slug":"flowhigh-towards-efficient-and-high-quality","title":"FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow Matching","date":"2025-01-09","arxiv_id":"2501.04926","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":3,"n_no_contract":5,"n_pointer_only":6,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 3 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/flowhigh-towards-efficient-and-high-quality#ran","syntology_url":"https://syntology.ai/paper/2501.04926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.04926"}},"official":{"repos":["jjunak-yun/FLowHigh_code"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/time-graph-frequency-representation-with","slug":"time-graph-frequency-representation-with","title":"Time-Graph Frequency Representation with Singular Value Decomposition for Neural Speech Enhancement","date":"2024-12-22","arxiv_id":"2412.16823","repositories_listed":1,"syntology":null},{"url":"/paper/mamba-seunet-mamba-unet-for-monaural-speech","slug":"mamba-seunet-mamba-unet-for-monaural-speech","title":"Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancement","date":"2024-12-21","arxiv_id":"2412.16626","repositories_listed":1,"syntology":null},{"url":"/paper/source-separation-automatic-transcription-for","slug":"source-separation-automatic-transcription-for","title":"Source Separation & Automatic Transcription for Music","date":"2024-12-09","arxiv_id":"2412.06703","repositories_listed":1,"syntology":null},{"url":"/paper/explainable-dnn-based-beamformer-with","slug":"explainable-dnn-based-beamformer-with","title":"Explainable DNN-based Beamformer with Postfilter","date":"2024-11-16","arxiv_id":"2411.10854","repositories_listed":1,"syntology":null},{"url":"/paper/towards-ultra-low-power-neuromorphic-speech","slug":"towards-ultra-low-power-neuromorphic-speech","title":"Towards Ultra-Low-Power Neuromorphic Speech Enhancement with Spiking-FullSubNet","date":"2024-10-07","arxiv_id":"2410.04785","repositories_listed":1,"syntology":null},{"url":"/paper/lisennet-lightweight-sub-band-and-dual-path","slug":"lisennet-lightweight-sub-band-and-dual-path","title":"LiSenNet: Lightweight Sub-band and Dual-Path Modeling for Real-Time Speech Enhancement","date":"2024-09-20","arxiv_id":"2409.13285","repositories_listed":1,"syntology":null},{"url":"/paper/a-lightweight-and-real-time-binaural-speech","slug":"a-lightweight-and-real-time-binaural-speech","title":"A Lightweight and Real-Time Binaural Speech Enhancement Model with Spatial Cues Preservation","date":"2024-09-19","arxiv_id":"2409.12444","repositories_listed":1,"syntology":null},{"url":"/paper/high-resolution-speech-restoration-with","slug":"high-resolution-speech-restoration-with","title":"High-Resolution Speech Restoration with Latent Diffusion Model","date":"2024-09-17","arxiv_id":"2409.11145","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-training-objectives-for","slug":"investigating-training-objectives-for","title":"Investigating Training Objectives for Generative Speech Enhancement","date":"2024-09-16","arxiv_id":"2409.10753","repositories_listed":1,"syntology":null},{"url":"/paper/apollo-band-sequence-modeling-for-high","slug":"apollo-band-sequence-modeling-for-high","title":"Apollo: Band-sequence Modeling for High-Quality Audio Restoration","date":"2024-09-13","arxiv_id":"2409.08514","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/apollo-band-sequence-modeling-for-high#ran","syntology_url":"https://syntology.ai/paper/2409.08514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.08514"}},"official":{"repos":["jusperlee/apollo"],"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"]}}},{"url":"/paper/indicvoices-r-unlocking-a-massive","slug":"indicvoices-r-unlocking-a-massive","title":"IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS","date":"2024-09-09","arxiv_id":"2409.05356","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/indicvoices-r-unlocking-a-massive#ran","syntology_url":"https://syntology.ai/paper/2409.05356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05356"}},"official":{"repos":["ai4bharat/indicvoices-r"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/effective-noise-aware-data-simulation-for","slug":"effective-noise-aware-data-simulation-for","title":"Effective Noise-aware Data Simulation for Domain-adaptive Speech Enhancement Leveraging Dynamic Stochastic Perturbation","date":"2024-09-03","arxiv_id":"2409.01545","repositories_listed":1,"syntology":null},{"url":"/paper/lstmse-net-long-short-term-speech-enhancement","slug":"lstmse-net-long-short-term-speech-enhancement","title":"LSTMSE-Net: Long Short Term Speech Enhancement Network for Audio-visual Speech Enhancement","date":"2024-09-03","arxiv_id":"2409.02266","repositories_listed":1,"syntology":null},{"url":"/paper/bss-cffma-cross-domain-feature-fusion-and","slug":"bss-cffma-cross-domain-feature-fusion-and","title":"BSS-CFFMA: Cross-Domain Feature Fusion and Multi-Attention Speech Enhancement Network based on Self-Supervised Embedding","date":"2024-08-13","arxiv_id":"2408.06851","repositories_listed":1,"syntology":null},{"url":"/paper/direction-of-arrival-correction-through","slug":"direction-of-arrival-correction-through","title":"Direction of Arrival Correction through Speech Quality Feedback","date":"2024-08-13","arxiv_id":"2408.07234","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null}],"syntology_records":29,"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":2,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/speech-enhancement-on-demand","since_archive":"/sota/speech-enhancement-on-demand#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/speech-enhancement-on-voicebank-demand-2","since_archive":"/sota/speech-enhancement-on-voicebank-demand-2#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/speech-enhancement-on-demand-1","since_archive":"/sota/speech-enhancement-on-demand-1#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":54,"papers_where_code_ran_first_page":"/task/speech-enhancement/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":"archive","page":2,"of":10,"url":"/task/speech-enhancement/papers/2","json":"/task/speech-enhancement/papers/2.json","rows":100},{"order":"archive","page":3,"of":10,"url":"/task/speech-enhancement/papers/3","json":"/task/speech-enhancement/papers/3.json","rows":100},{"order":"archive","page":4,"of":10,"url":"/task/speech-enhancement/papers/4","json":"/task/speech-enhancement/papers/4.json","rows":100},{"order":"archive","page":5,"of":10,"url":"/task/speech-enhancement/papers/5","json":"/task/speech-enhancement/papers/5.json","rows":100},{"order":"archive","page":6,"of":10,"url":"/task/speech-enhancement/papers/6","json":"/task/speech-enhancement/papers/6.json","rows":100},{"order":"archive","page":7,"of":10,"url":"/task/speech-enhancement/papers/7","json":"/task/speech-enhancement/papers/7.json","rows":100},{"order":"archive","page":8,"of":10,"url":"/task/speech-enhancement/papers/8","json":"/task/speech-enhancement/papers/8.json","rows":100},{"order":"archive","page":9,"of":10,"url":"/task/speech-enhancement/papers/9","json":"/task/speech-enhancement/papers/9.json","rows":100},{"order":"archive","page":10,"of":10,"url":"/task/speech-enhancement/papers/10","json":"/task/speech-enhancement/papers/10.json","rows":82},{"order":"ran","page":1,"of":1,"url":"/task/speech-enhancement/papers/ran/1","json":"/task/speech-enhancement/papers/ran/1.json","rows":54}],"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":"8c00771be9d8a3c50431414b40ab201e4645fb6e2ee248a53310b09c58a9b45b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}