{"url":"/dataset/deep-noise-suppression-2020","name":"DNS Challenge","full_name":"Deep Noise Suppression Challenge","description_markdown":"The DNS Challenge at INTERSPEECH 2020 intended to promote collaborative research in single-channel Speech Enhancement aimed to maximize the perceptual quality and intelligibility of the enhanced speech. The challenge evaluated the speech quality using the online subjective evaluation framework ITU-T P.808. The challenge provides large datasets for training noise suppressors.\r\n\r\nSource: [Deep Noise Suppression Challenge – INTERSPEECH 2020](https://www.microsoft.com/en-us/research/academic-program/deep-noise-suppression-challenge-interspeech-2020/)","description_withheld":null,"homepage":"https://www.microsoft.com/en-us/research/academic-program/deep-noise-suppression-challenge-interspeech-2020/","introduced_date":"2020-01-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-interspeech-2020-deep-noise-suppression","title":"The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Speech Quality and Testing Framework","first_author":"Chandan K. A. Reddy","url":null},"license":null,"modalities":[],"tasks":[{"name":"Speech Enhancement","url":"/task/speech-enhancement","datasets_with_task":"/datasets/task/speech-enhancement"},{"name":"Audio Source Separation","url":"/task/audio-source-separation","datasets_with_task":"/datasets/task/audio-source-separation"},{"name":"Speech Dereverberation","url":"/task/speech-dereverberation","datasets_with_task":"/datasets/task/speech-dereverberation"}],"languages":[],"variants":["Deep Noise Suppression (DNS) Challenge","DNS Challenge","ICASSP 2021 Deep Noise Suppression Challenge","Interspeech 2021 Deep Noise Suppression Challenge"],"data_loaders":[],"num_papers_in_archive":48,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-enhancement-on-deep-noise-suppression","task":"Speech Enhancement","dataset_variant":"Deep Noise Suppression (DNS) Challenge","rows":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":null,"metrics":{"FLOPS (G)":"266.96","Number of parameters (M)":"11.34","PESQ-NB":"4.08","PESQ-WB":"3.81","SI-SDR-WB":"22.22","STOI":"98.65"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-enhancement-on-interspeech-2020-deep","task":"Speech Enhancement","dataset_variant":"DNS Challenge","rows":5,"metrics":["PESQ-NB","PESQ-WB"],"first_row_in_archive_order":{"model":"ZipEnhancer\n(M)","paper":null,"metrics":{"PESQ-NB":"4.08","PESQ-WB":"3.81"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-dereverberation-on-deep-noise","task":"Speech Dereverberation","dataset_variant":"Deep Noise Suppression (DNS) Challenge","rows":2,"metrics":["PESQ","ΔPESQ"],"first_row_in_archive_order":{"model":"Conv-TasNet-SNR","paper":"/paper/exploring-the-best-loss-function-for-dnn-1","metrics":{"PESQ":"2.75","ΔPESQ":"0.93"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mambattention-mamba-with-multi-head-attention","title":"MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement","date":"2025-07-01","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/raw-speech-enhancement-with-deep-state-space","title":"aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audio","date":"2024-09-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/tf-locoformer-transformer-with-local-modeling","title":"TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement","date":"2024-08-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cleanunet-2-a-hybrid-speech-denoising-model","title":"CleanUNet 2: A Hybrid Speech Denoising Model on Waveform and Spectrogram","date":"2023-09-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":13,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-mask-free-neural-network-for-monaural","title":"A Mask Free Neural Network for Monaural Speech Enhancement","date":"2023-06-07","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/high-fidelity-speech-enhancement-with-band","title":"High Fidelity Speech Enhancement with Band-split RNN","date":"2022-12-01","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/fullsubnet-channel-attention-fullsubnet-with","title":"FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement","date":"2022-03-23","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/remixit-continual-self-training-of-speech","title":"RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing","date":"2022-02-17","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/speech-denoising-in-the-waveform-domain-with","title":"Speech Denoising in the Waveform Domain with Self-Attention","date":"2022-02-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/continual-self-training-with-bootstrapped","title":"Continual self-training with bootstrapped remixing for speech enhancement","date":"2021-10-19","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/real-time-monaural-speech-enhancement-with","title":"Real-time Monaural Speech Enhancement With Short-time Discrete Cosine Transform","date":"2021-02-09","rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/interactive-speech-and-noise-modeling-for-1","title":"Interactive Speech and Noise Modeling for Speech Enhancement","date":"2020-12-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/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","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":21,"samples_ran":1,"samples_unverified":20,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/exploring-the-best-loss-function-for-dnn-1","title":"Exploring the Best Loss Function for DNN-Based Low-latency Speech Enhancement with Temporal Convolutional Networks","date":"2020-08-20","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/poconet-better-speech-enhancement-with","title":"PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Loss","date":"2020-08-11","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/weighted-speech-distortion-losses-for-neural-1","title":"Weighted Speech Distortion Losses for Neural-network-based Real-time Speech Enhancement","date":"2020-02-12","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/dual-signal-transformation-lstm-network-for","title":"Dual-Signal Transformation LSTM Network for Real-Time Noise Suppression","date":null,"rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dccrn-deep-complex-convolution-recurrent-1","title":"DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement","date":null,"rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":5,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":7,"samples_harvested":61,"samples_ran":22,"samples_unverified":39,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":2,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}