{"url":"/dataset/shd","name":"SHD","full_name":"Spiking Heidelberg Digits","description_markdown":"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.\r\n\r\nCramer, 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.","description_withheld":null,"homepage":"https://zenkelab.org/resources/spiking-heidelberg-datasets-shd/","introduced_date":"2019-10-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-heidelberg-spiking-datasets-for-the","title":"The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks","first_author":"Benjamin Cramer","url":null},"license":null,"modalities":[],"tasks":[{"name":"Audio Classification","url":"/task/audio-classification","datasets_with_task":"/datasets/task/audio-classification"}],"languages":[],"variants":["SHD"],"data_loaders":[],"num_papers_in_archive":19,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/audio-classification-on-shd","task":"Audio Classification","dataset_variant":"SHD","rows":11,"metrics":["Percentage correct"],"first_row_in_archive_order":{"model":"Event-SSM","paper":"/paper/scalable-event-by-event-processing-of","metrics":{"Percentage correct":"95.9"},"code_links":[{"title":"Efficient-Scalable-Machine-Learning/event-ssm","url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/scalable-event-by-event-processing-of","title":"Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Models","date":"2024-04-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":18,"samples_ran":15,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-delays-in-spiking-neural-networks","title":"Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings","date":"2023-06-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adaptive-axonal-delays-in-feedforward-spiking","title":"Adaptive Axonal Delays in feedforward spiking neural networks for accurate spoken word recognition","date":"2023-02-16","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/stsc-snn-spatio-temporal-synaptic-connection","title":"STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural Networks","date":"2022-10-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fluctuation-driven-initialization-for-spiking","title":"Fluctuation-driven initialization for spiking neural network training","date":"2022-06-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/accelerating-spiking-neural-network-training","title":"Robust and accelerated single-spike spiking neural network training with applicability to challenging temporal tasks","date":"2022-05-30","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/map-snn-mapping-spike-activities-with","title":"MAP-SNN: Mapping Spike Activities with Multiplicity, Adaptability, and Plasticity into Bio-Plausible Spiking Neural Networks","date":"2022-04-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/temporal-wise-attention-spiking-neural","title":"Temporal-wise Attention Spiking Neural Networks for Event Streams Classification","date":"2021-07-25","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sparse-spiking-gradient-descent","title":"Sparse Spiking Gradient Descent","date":"2021-05-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/the-heidelberg-spiking-datasets-for-the","title":"The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks","date":"2019-10-16","rows_on_this_dataset":2,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":22,"samples_ran":15,"samples_unverified":7,"pointer_only_for_licence":0,"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."}