Datasets › EARS-WHAM

EARS-WHAM

Introduced by Julius Richter et al. in EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation10 Jun 2024 archive 2025-07-28

The EARS-WHAM dataset mixes speech from the EARS dataset with real noise recordings from the WHAM! dataset. Speech and noise files are mixed at signal-to-noise ratios (SNRs) randomly sampled in a range of [−2.5, 17.5] dB, where the SNR is computed using loudness K- weighted relative to full scale (LKFS) standardized in ITU-R BS.1770 to obtain a more perceptually meaningful scaling and also to remove silent regions from the SNR computation.

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Speech Enhancement EARS-WHAM Schrödinger Bridge (PESQ loss) PESQ-WB 3.09 Investigating Training Objectives for Generative Speech... sp-uhh/sgmse 6 Compare

Papers archive 2025-07-28

6 shown of 6 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 11. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Investigating Training Objectives for Generative Speech Enhancement 1 1 16 Sep 2024 not harvested
Schrödinger Bridge for Generative Speech Enhancement 0 1 22 Jul 2024 not harvested
Hybrid Transformers for Music Source Separation 2 1 15 Nov 2022 ran 0 of 10 samples (10 unverified; 10 pointer-only for licence)
Speech Enhancement and Dereverberation with Diffusion-based Generative Models 1 1 11 Aug 2022 not harvested
Conditional Diffusion Probabilistic Model for Speech Enhancement 2 1 10 Feb 2022 not harvested
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation 17 1 20 Sep 2018 ran 7 of 36 samples (29 unverified; 16 pointer-only for licence)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

CC-NC 4.0 International license

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • EARS-WHAM

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections