SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1808.08929 · 2018

A neural attention model for speech command recognition

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1808.08929.json · badge: /api/ran/1808.08929.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
douglas125/SpeechCmdRecognition canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
renyuanL/ry-Speech-commands reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
normalize Ran
ran, honoured the contract we drafted
renyuanL/ry-Speech-commands/ryRecog03.py
pointer only (licence: GPL-3.0) · get_code("720014c5cc086010")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, renyuanL/ry-Speech-commands, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

predict_audio Ran
ran; our contract draft was wrong, not the code
douglas125/SpeechCmdRecognition/recognize_word.py
code served (permissive licence) · get_code("57c9801112b59c24")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

class MockAudioModel:
    """Mock model that mimics TensorFlow/Keras model behavior."""
    def predict(self, audio_data):
        # Return predictions with shape (batch_size, num_classes)
        # argmax will be computed, then subtract 1, so we need valid indices
        batch_size = audio_data.shape[0] if len(audio_data.shape) > 0 else 1
        num_classes = len(categories)
        # Return random predictions that will give valid indices after -1
        predictions = np.random.rand(batch_size, num_classes)
        return predictions

# Create mock model
model = MockAudioModel()

# Create mock audio data - batch of 2 audio samples with 4 features each
audio_data = np.random.rand(2, 4).astype(np.float32)

ARGS = {
    'model': model,
    'audio_data': audio_data,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
ryGet1secSpeech Not yet run
unverified (harvested, no recorded run)
renyuanL/ry-Speech-commands/ryRealTimeAsr03.py
pointer only (licence: GPL-3.0) · get_code("6fa05e75f626df54")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, renyuanL/ry-Speech-commands, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper introduces a convolutional recurrent network with attention for speech command recognition. Attention models are powerful tools to improve performance on natural language, image captioning and speech tasks. The proposed model establishes a new state-of-the-art accuracy of 94.1% on Google Speech Commands dataset V1 and 94.5% on V2 (for the 20-commands recognition task), while still keeping a small footprint of only 202K trainable parameters. Results are compared with previous convolutional implementations on 5 different tasks (20 commands recognition (V1 and V2), 12 commands recognition (V1), 35 word recognition (V1) and left-right (V1)). We show detailed performance results and demonstrate that the proposed attention mechanism not only improves performance but also allows inspecting what regions of the audio were taken into consideration by the network when outputting a given category.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1808.08929")
get_code_for_paper("1808.08929")
have("1808.08929")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1808.08929.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1808.08929.svg)](https://syntology.ai/paper/1808.08929)

Connect an agent — have() is free.