{"url":"/task/speech-denoising","name":"Speech Denoising","slug":"speech-denoising","description_markdown":"Obtain the clean speech of the target speaker by suppressing the background noise. Recent representative github platform [ClearerVoice-Studio](https://github.com/modelscope/ClearerVoice-Studio)","categories":[{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":65,"papers_with_code":32,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/speech-denoising-on-lrs2-vggsound","slug":"speech-denoising-on-lrs2-vggsound","dataset":"LRS2+VGGSound","dataset_url":null,"rows_in_archive":1,"metrics":["CBAK","COVL","CSIG","PESQ","STOI"],"first_row_in_archive_order":{"model":null,"paper_title":"Visual Speech Enhancement Without A Real Visual Stream","paper_url":"/paper/visual-speech-enhancement-without-a-real","paper_date":"2020-12-20","arxiv_id":"2012.10852","code_links":[{"title":"Sindhu-Hegde/pseudo-visual-speech-denoising","url":"https://github.com/Sindhu-Hegde/pseudo-visual-speech-denoising"}],"syntology":null}},{"leaderboard":"/sota/speech-denoising-on-lrs3-vggsound","slug":"speech-denoising-on-lrs3-vggsound","dataset":"LRS3+VGGSound","dataset_url":null,"rows_in_archive":1,"metrics":["CBAK","COVL","CSIG","PESQ","STOI"],"first_row_in_archive_order":{"model":null,"paper_title":"Visual Speech Enhancement Without A Real Visual Stream","paper_url":"/paper/visual-speech-enhancement-without-a-real","paper_date":"2020-12-20","arxiv_id":"2012.10852","code_links":[{"title":"Sindhu-Hegde/pseudo-visual-speech-denoising","url":"https://github.com/Sindhu-Hegde/pseudo-visual-speech-denoising"}],"syntology":null}}],"datasets":[{"url":"/dataset/emospeech","name":"EmoSpeech","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/whamr-ext","name":"WHAMR_ext","full_name":"WHAMR_ext","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":32,"tagged_in_all":65,"items":[{"url":"/paper/wavlm-large-scale-self-supervised-pre","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","date":"2021-10-26","arxiv_id":"2110.13900","repositories_listed":9,"syntology":null},{"url":"/paper/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/speech-denoising-with-deep-feature-losses","title":"Speech Denoising with Deep Feature Losses","date":"2018-06-27","arxiv_id":"1806.10522","repositories_listed":5,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/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/fra-rir-fast-random-approximation-of-the","title":"FRA-RIR: Fast Random Approximation of the Image-source Method","date":"2022-08-08","arxiv_id":"2208.04101","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","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/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/joint-optimization-of-masks-and-deep","title":"Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation","date":"2015-02-13","arxiv_id":"1502.04149","repositories_listed":2,"syntology":null},{"url":"/paper/cleanumamba-a-compact-mamba-network-for","title":"CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel Pruning","date":"2024-10-14","arxiv_id":"2410.11062","repositories_listed":1,"syntology":null},{"url":"/paper/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/generative-speech-foundation-model","title":"Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration","date":"2024-09-24","arxiv_id":"2409.16117","repositories_listed":1,"syntology":null},{"url":"/paper/explicit-estimation-of-magnitude-and-phase","title":"Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement","date":"2023-08-17","arxiv_id":"2308.08926","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/miipher-a-robust-speech-restoration-model","title":"Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations","date":"2023-03-03","arxiv_id":"2303.01664","repositories_listed":1,"syntology":null},{"url":"/paper/analysing-diffusion-based-generative","title":"Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restoration","date":"2022-11-04","arxiv_id":"2211.02397","repositories_listed":1,"syntology":null},{"url":"/paper/speech-dereverberation-with-a-reverberation","title":"Speech Dereverberation with a Reverberation Time Shortening Target","date":"2022-10-20","arxiv_id":"2210.11089","repositories_listed":1,"syntology":null},{"url":"/paper/birdsoundsdenoising-deep-visual-audio","title":"BirdSoundsDenoising: Deep Visual Audio Denoising for Bird Sounds","date":"2022-10-18","arxiv_id":"2210.10196","repositories_listed":1,"syntology":null},{"url":"/paper/voicefixer-a-unified-framework-for-high","title":"VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration","date":"2022-04-12","arxiv_id":"2204.05841","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/speech-denoising-in-the-waveform-domain-with","title":"Speech Denoising in the Waveform Domain with Self-Attention","date":"2022-02-15","arxiv_id":"2202.07790","repositories_listed":1,"syntology":null},{"url":"/paper/task-specific-optimization-of-virtual-channel","title":"Task-specific Optimization of Virtual Channel Linear Prediction-based Speech Dereverberation Front-End for Far-Field Speaker Verification","date":"2021-12-27","arxiv_id":"2112.13569","repositories_listed":1,"syntology":null},{"url":"/paper/speech-denoising-using-only-single-noisy","title":"Self-Supervised Speech Denoising Using Only Noisy Audio Signals","date":"2021-10-30","arxiv_id":"2111.00242","repositories_listed":1,"syntology":null},{"url":"/paper/a-modulation-domain-loss-for-neural-network-1","title":"A Modulation-Domain Loss for Neural-Network-based Real-time Speech Enhancement","date":"2021-02-15","arxiv_id":"2102.07330","repositories_listed":1,"syntology":null},{"url":"/paper/visual-speech-enhancement-without-a-real","title":"Visual Speech Enhancement Without A Real Visual Stream","date":"2020-12-20","arxiv_id":"2012.10852","repositories_listed":1,"syntology":null},{"url":"/paper/speech-denoising-with-auditory-models","title":"Speech Denoising with Auditory Models","date":"2020-11-21","arxiv_id":"2011.10706","repositories_listed":1,"syntology":null},{"url":"/paper/listening-to-sounds-of-silence-for-speech","title":"Listening to Sounds of Silence for Speech Denoising","date":"2020-10-22","arxiv_id":"2010.12013","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":6}},{"url":"/paper/perceptual-loss-based-speech-denoising-with","title":"Perceptual Loss based Speech Denoising with an ensemble of Audio Pattern Recognition and Self-Supervised Models","date":"2020-10-22","arxiv_id":"2010.11860","repositories_listed":1,"syntology":null},{"url":"/paper/phase-aware-single-stage-speech-denoising-and-1","title":"Phase-aware Single-stage Speech Denoising and Dereverberation with U-Net","date":"2020-06-01","arxiv_id":"2006.00687","repositories_listed":1,"syntology":null},{"url":"/paper/sparse-mixture-of-local-experts-for-efficient","title":"Sparse Mixture of Local Experts for Efficient Speech Enhancement","date":"2020-05-16","arxiv_id":"2005.08128","repositories_listed":1,"syntology":null},{"url":"/paper/boosted-locality-sensitive-hashing","title":"Boosted Locality Sensitive Hashing: Discriminative Binary Codes for Source Separation","date":"2020-02-14","arxiv_id":"2002.06239","repositories_listed":1,"syntology":null},{"url":"/paper/audio-denoising-with-deep-network-priors","title":"Speech Denoising by Accumulating Per-Frequency Modeling Fluctuations","date":"2019-04-16","arxiv_id":"1904.07612","repositories_listed":1,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}