Datasets › SHD

SHD (Spiking Heidelberg Digits)

Introduced by Benjamin Cramer et al. in The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks16 Oct 2019 archive 2025-07-28

The Spiking Heidelberg Digits (SHD) dataset is an audio-based classification dataset of 1k spoken digits ranging from zero to nine in the English and German languages. The audio waveforms have been converted into spike trains using an artificial model of the inner ear and parts of the ascending auditory pathway. The SHD dataset has 8,156 training and 2,264 test samples. A full description of the dataset and how it was created can be found in the paper below. Please cite this paper if you make use of the dataset.

Cramer, B.; Stradmann, Y.; Schemmel, J.; and Zenke, F. "The Heidelberg Spiking Data Sets for the Systematic Evaluation of Spiking Neural Networks". IEEE Transactions on Neural Networks and Learning Systems 33, 2744–2757, 2022.

Homepage Benchmarks Papers JSON

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)	Paper	Code
Audio Classification	SHD	Event-SSM Percentage correct 95.9	Scalable Event-by-event Processing of Neuromorphic...	Efficient-Scalable-Machine-Learning/event-ssm	11	Compare

Papers archive 2025-07-28

10 shown of 10 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 19. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

			Date	Samples run Syntology
Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models	1	1	29 Apr 2024	ran 15 of 18 samples (3 unverified)
Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings	1	1	30 Jun 2023	not harvested
Adaptive Axonal Delays in feedforward spiking neural networks for accurate spoken word recognition	0	1	16 Feb 2023	not harvested
STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural Networks	1	1	11 Oct 2022	not harvested
Fluctuation-driven initialization for spiking neural network training	1	1	21 Jun 2022	ran 0 of 2 samples (2 unverified)
Robust and accelerated single-spike spiking neural network training with applicability to challenging temporal tasks	1	1	30 May 2022	ran 0 of 2 samples (2 unverified)
MAP-SNN: Mapping Spike Activities with Multiplicity, Adaptability, and Plasticity into Bio-Plausible Spiking Neural Networks	1	1	21 Apr 2022	not harvested
Temporal-wise Attention Spiking Neural Networks for Event Streams Classification	0	1	25 Jul 2021	not harvested
Sparse Spiking Gradient Descent	1	1	18 May 2021	not harvested
The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks	0	2	16 Oct 2019	not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Audio Classification

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

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