{"url":"/task/speech-dereverberation","name":"Speech Dereverberation","slug":"speech-dereverberation","description_markdown":"Removing reverberation from audio signals","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":50,"papers_with_code":20,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"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":6,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/speech-dereverberation-on-whamr","slug":"speech-dereverberation-on-whamr","dataset":"WHAMR!","dataset_url":"/dataset/whamr","rows_in_archive":3,"metrics":["PESQ","SI-SDR","ESTOI","SRMR","SI-SDRi"],"first_row_in_archive_order":{"model":"WD-TCN","paper_title":"Utterance Weighted Multi-Dilation Temporal Convolutional Networks for Monaural Speech Dereverberation","paper_url":"/paper/utterance-weighted-multi-dilation-temporal","paper_date":"2022-05-17","arxiv_id":"2205.08455","code_links":[{"title":"jwr1995/wd-tcn","url":"https://github.com/jwr1995/wd-tcn"}],"syntology":null}},{"leaderboard":"/sota/speech-dereverberation-on-deep-noise","slug":"speech-dereverberation-on-deep-noise","dataset":"Deep Noise Suppression (DNS) Challenge","dataset_url":"/dataset/deep-noise-suppression-2020","rows_in_archive":2,"metrics":["PESQ","ΔPESQ"],"first_row_in_archive_order":{"model":"Conv-TasNet-SNR","paper_title":"Exploring the Best Loss Function for DNN-Based Low-latency Speech Enhancement with Temporal Convolutional Networks","paper_url":"/paper/exploring-the-best-loss-function-for-dnn-1","paper_date":"2020-08-20","arxiv_id":"2005.11611","code_links":[],"syntology":null}},{"leaderboard":"/sota/speech-dereverberation-on-ears-reverb","slug":"speech-dereverberation-on-ears-reverb","dataset":"EARS-Reverb","dataset_url":"/dataset/ears-reverb","rows_in_archive":1,"metrics":["PESQ-WB","SI-SDR","ESTOI","SIGMOS","MOS Reverb"],"first_row_in_archive_order":{"model":"SGMSE+","paper_title":"Speech Enhancement and Dereverberation with Diffusion-based Generative Models","paper_url":"/paper/speech-enhancement-and-dereverberation-with","paper_date":"2022-08-11","arxiv_id":"2208.05830","code_links":[{"title":"sp-uhh/sgmse","url":"https://github.com/sp-uhh/sgmse"}],"syntology":null}},{"leaderboard":"/sota/speech-dereverberation-on-spatialized-wsjcam0","slug":"speech-dereverberation-on-spatialized-wsjcam0","dataset":"spatialized WSJCAM0","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-dereverberation-on-whamr-ext","slug":"speech-dereverberation-on-whamr-ext","dataset":"WHAMR_ext","dataset_url":"/dataset/whamr-ext","rows_in_archive":1,"metrics":["ESTOI","PESQ","SI-SDR","SI-SDRi","SRMR"],"first_row_in_archive_order":{"model":"Conv-TasNet DAE","paper_title":"Receptive Field Analysis of Temporal Convolutional Networks for Monaural Speech Dereverberation","paper_url":"/paper/receptive-field-analysis-of-temporal","paper_date":"2022-04-13","arxiv_id":"2204.06439","code_links":[{"title":"jwr1995/whamr_ext","url":"https://github.com/jwr1995/whamr_ext"}],"syntology":null}}],"datasets":[{"url":"/dataset/wham","name":"WHAM!","full_name":"WSJ0 Hipster Ambient Mixtures","num_papers_in_archive":114},{"url":"/dataset/whamr","name":"WHAMR!","full_name":"WHAM! with synthetic reverberated sources","num_papers_in_archive":57},{"url":"/dataset/deep-noise-suppression-2020","name":"DNS Challenge","full_name":"Deep Noise Suppression Challenge","num_papers_in_archive":48},{"url":"/dataset/ears-reverb","name":"EARS-Reverb","full_name":"","num_papers_in_archive":2},{"url":"/dataset/reverb-wsj0","name":"Reverb-WSJ0","full_name":"","num_papers_in_archive":2},{"url":"/dataset/whamr-ext","name":"WHAMR_ext","full_name":"WHAMR_ext","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/speech-enhancement","name":"Speech Enhancement"}],"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":20,"of":20,"tagged_in_all":50,"items":[{"url":"/paper/av-rir-audio-visual-room-impulse-response","title":"AV-RIR: Audio-Visual Room Impulse Response Estimation","date":"2023-11-30","arxiv_id":"2312.00834","repositories_listed":2,"syntology":null},{"url":"/paper/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":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/deformable-temporal-convolutional-networks","title":"Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation","date":"2022-10-27","arxiv_id":"2210.15305","repositories_listed":2,"syntology":null},{"url":"/paper/mesh2ir-neural-acoustic-impulse-response","title":"MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes","date":"2022-05-18","arxiv_id":"2205.09248","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":6}},{"url":"/paper/vinp-variational-bayesian-inference-with","title":"VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification","date":"2025-02-11","arxiv_id":"2502.07205","repositories_listed":1,"syntology":null},{"url":"/paper/acoustic-modeling-for-overlapping-speech","title":"Acoustic modeling for Overlapping Speech Recognition: JHU Chime-5 Challenge System","date":"2024-05-17","arxiv_id":"2405.11078","repositories_listed":1,"syntology":null},{"url":"/paper/rvae-em-generative-speech-dereverberation","title":"RVAE-EM: Generative speech dereverberation based on recurrent variational auto-encoder and convolutive transfer function","date":"2023-09-15","arxiv_id":"2309.08157","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/deft-an-dense-frequency-time-attentive","title":"DeFT-AN: Dense Frequency-Time Attentive Network for Multichannel Speech Enhancement","date":"2022-12-15","arxiv_id":"2212.07570","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/speech-enhancement-and-dereverberation-with","title":"Speech Enhancement and Dereverberation with Diffusion-based Generative Models","date":"2022-08-11","arxiv_id":"2208.05830","repositories_listed":1,"syntology":null},{"url":"/paper/utterance-weighted-multi-dilation-temporal","title":"Utterance Weighted Multi-Dilation Temporal Convolutional Networks for Monaural Speech Dereverberation","date":"2022-05-17","arxiv_id":"2205.08455","repositories_listed":1,"syntology":null},{"url":"/paper/receptive-field-analysis-of-temporal","title":"Receptive Field Analysis of Temporal Convolutional Networks for Monaural Speech Dereverberation","date":"2022-04-13","arxiv_id":"2204.06439","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/late-reverberation-suppression-using-u-nets","title":"Late reverberation suppression using U-nets","date":"2021-10-05","arxiv_id":"2110.02144","repositories_listed":1,"syntology":null},{"url":"/paper/blind-room-parameter-estimation-using","title":"Blind Room Parameter Estimation Using Multiple-Multichannel Speech Recordings","date":"2021-07-29","arxiv_id":"2107.13832","repositories_listed":1,"syntology":null},{"url":"/paper/hifi-gan-high-fidelity-denoising-and","title":"HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks","date":"2020-06-10","arxiv_id":"2006.05694","repositories_listed":1,"syntology":null},{"url":"/paper/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,"repositories_listed":1,"syntology":null},{"url":"/paper/investigating-generative-adversarial-networks","title":"Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition","date":"2018-03-27","arxiv_id":"1803.10132","repositories_listed":1,"syntology":null}],"syntology_records":3,"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"}}