Keyword Spotting on SHD

Dataset

The Spiking Heidelberg Digits (SHD) dataset contains recordings of spoken digits (0–9 in English and German, 20 classes total) converted to spike trains by a cochlear model. Each sample consists of events from 700 auditory channels over a variable duration. The dataset is available under CC BY 4.0.

Property	Value
Classes	20 (10 digits × 2 languages)
Input channels	700 cochlea channels
Training samples	8,156
Test samples	2,264
Event format	`(timestamp_s, channel_index)` pairs

Architecture

Dense(700 → 512) → LIF(τ_mem=20ms, threshold=0.3) → Dense(512 → 20) → LIF(τ_mem=20ms, threshold=0.3)

Two hidden layers, feedforward, no recurrence. This matches the architecture class in Zheng et al. 2025’s “without conditions” category. Why threshold=0.3? SHD has ~0.3–0.7% spike density per bin — about 20× sparser than rate-encoded image data. A threshold of 1.0 (suited for dense inputs) produces zero firing on SHD: neurons never accumulate enough charge to spike, and no gradient flows. 0.3 places the firing threshold where surrogate gradients can flow from the first epoch.

Preprocessing

Each SHD sample is a stream of (time_s, channel) events. We bin them into T=100 discrete timesteps at 14 ms per bin (matching the 1.4s maximum sample duration):

def bin_sample(spike_times, spike_units, T=100, max_time=1.4):
    dt = max_time / T
    dense = torch.zeros(T, 700)
    for t_s, u in zip(spike_times, spike_units):
        t = min(int(t_s / dt), T - 1)
        if u < 700:
            dense[t, u] = 1.0
    return dense

Multiple spikes in the same bin and channel are deduplicated (the bin is already 1.0 after the first event).

Training

The complete training script is at templates/keyword-spotting/train.py. Key hyperparameters:

Parameter	Value
Optimizer	Adam
Learning rate	1×10⁻³
Gradient clip	norm ≤ 5.0
Batch size	64
Epochs	100
Loss	Cross-entropy on mean firing rates

import thrindex.snn as snn
from thrindex.train import rate_loss

model = snn.Sequential(
    snn.Dense(700, 512),
    snn.LIF(tau_mem=20.0, threshold=0.3),
    snn.Dense(512, 20),
    snn.LIF(tau_mem=20.0, threshold=0.3),
)

optimizer = torch.optim.Adam(model.parameters(), lr=1e-3)

for x, y in train_loader:
    out = model(x)
    loss = rate_loss(out, y)
    loss.backward()
    torch.nn.utils.clip_grad_norm_(model.parameters(), 5.0)
    optimizer.step()
    optimizer.zero_grad()

uv run python templates/keyword-spotting/train.py \
    --data-dir /tmp/shd --epochs 100

The script downloads the dataset automatically on first run.

Results

Run	Test accuracy	Hardware
thrindex M2 (2026-07-09)	64.66%	Apple M4 Pro (MPS)

Reference band (Zheng et al. 2025, feedforward LIF without special conditions): 63.2–74.8%. The committed result sits within this band, confirming the surrogate-gradient LIF implementation is correct for sparse event-based inputs. See benchmarks/spiking-heidelberg-digits for the full epoch curve and comparisons.

Learning curve highlights

The network learns rapidly in the first 14 epochs (21% → 64.66% best) and then enters a noisy plateau. This is characteristic of feedforward LIF on SHD: the small training set (8,156 samples) and absence of regularisation limit further gains. The best checkpoint is saved and compiled.

Compile and run

import thrindex as thx
thx.compile(model, "templates/keyword-spotting/model.thx")

thrindex run templates/keyword-spotting/model.thx

The artifact at templates/keyword-spotting/model.thx contains the weights from the committed training run. Three real SHD test samples are bundled in templates/keyword-spotting/samples/ for offline inference.

What to try next

Increase hidden size to 1024 and observe the accuracy improvement.
Add a learning rate schedule (CosineAnnealingLR) — empirically improves stability after epoch 30.
Reduce tau_mem to 10ms and observe faster but noisier dynamics.

Getting Started

Tutorials

Concepts

Systems

API Reference

Errors

Benchmarks

Conformance

Keyword Spotting on SHD

Dataset

Architecture

Preprocessing

Training

Results

Learning curve highlights

Compile and run

What to try next

​Dataset

​Architecture

​Preprocessing

​Training

​Results

​Learning curve highlights

​Compile and run

​What to try next

Dataset

Architecture

Preprocessing

Training

Results

Learning curve highlights

Compile and run

What to try next