Papers › Snips Voice Platform: an embedded Spoken Language Understanding system for...

Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces

25 May 2018arXiv:1805.10190archive 2025-07-28

Alice Coucke, Alaa Saade, Adrien Ball, Théodore Bluche, Alexandre Caulier, David Leroy, Clément Doumouro, Thibault Gisselbrecht, Francesco Caltagirone, Thibaut Lavril, Maël Primet, Joseph Dureau

This paper presents the machine learning architecture of the Snips Voice Platform, a software solution to perform Spoken Language Understanding on microprocessors typical of IoT devices. The embedded inference is fast and accurate while enforcing privacy by design, as no personal user data is ever collected. Focusing on Automatic Speech Recognition and Natural Language Understanding, we detail our approach to training high-performance Machine Learning models that are small enough to run in real-time on small devices. Additionally, we describe a data generation procedure that provides sufficient, high-quality training data without compromising user privacy.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 3 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 6 ran (6 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 8 samples from 2 repositories, 7 ran (6 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 13 samples that ran has no recorded date.

16 repositories listed; official and paper-mentioned ones first.

snipsco/nlu-benchmark officialmentioned in papermentioned on GitHubCC0-1.0Syntology: not harvested report
snipsco/snips-nlu officialmentioned in papermentioned on GitHubApache-2.0Syntology: 7 samples, 6 ran (0 instrument-failed) · 1 unverified report
MiuLab/SlotGated-SLU mentioned on GitHubtfSyntology: not harvested report
Nilanshrajput/Intent_classification mentioned on GitHubpytorchSyntology: not harvested report
Priyanshiguptaaa/Intent_Recognition_BERT mentioned on GitHubtfSyntology: not harvested report
RezisEwig/unity_speech mentioned on GitHubSyntology: not harvested report
Rishabbh-Sahu/intent_and_slot_classification mentioned on GitHubtfSyntology: not harvested report
ai-agi/hicl mentioned on GitHubpytorchMITSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
aws-samples/aws-lex-noisy-spoken-language-understanding mentioned on GitHubCC0-1.0Syntology: not harvested report
levis0045/snips-nlu mentioned on GitHubApache-2.0Syntology: not harvested report
sonos/nlu-benchmark mentioned on GitHubCC0-1.0Syntology: not harvested report
switchsyj/adae2ml-xsf mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 4 ran (1 instrument-failed) · 0 unverified report
thuiar/textoir-demo mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
trusthlt/dp-rewrite mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to When differential privacy meets NLP: The devil is in the detail (arXiv:2109.03175; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
valerielimyh/Intent_Recognition_using_BERT mentioned on GitHubSyntology: not harvested report
zliucr/coach mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling (arXiv:2004.11727; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
12ran
2unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

snipsco/snips-nlu official repository 7 samples, 6 ran (0 instrument-failed) · 1 unverified
add_download_all_languages_parser snips_nlu/cli/download.py ran Apache-2.0 (permissive) · 2063007a0b14fda9 · report fixture: returned Mock · level recorded 2026-09-25
get_default_sep snips_nlu/languages.py ran fingerprinted Apache-2.0 (permissive) · 0890881a1809f989 · report fixture: signature language:str/0/str · returned str · level recorded 2026-09-25
get_punctuation snips_nlu/languages.py ran fingerprinted Apache-2.0 (permissive) · eb82a09f77baa167 · report fixture: signature language:str/0/str · returned str · level recorded 2026-09-25
get_punctuation_regex snips_nlu/languages.py ran Apache-2.0 (permissive) · b0193fffca67af2f · report fixture: signature language:str/0/str · returned Pattern · level recorded 2026-09-25
get_resources_sub_directory snips_nlu/resources.py ran Apache-2.0 (permissive) · c3fbe110100524d6 · report fixture: signature resources_dir:PosixPath/0/? · returned PosixPath · level recorded 2026-09-25
normalize_token snips_nlu/preprocessing.py ran Apache-2.0 (permissive) · c7d6a8799747fb75 · report fixture: signature token:Token/0/? · returned str · level recorded 2026-09-25
add_download_parser snips_nlu/cli/download.py unverified Apache-2.0 (permissive) · 930d5bac7e28fb59 · report
ai-agi/hicl community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
data_binarize src/_datareader.py ran MIT (permissive) · 18905af5183d3762 · report fixture: signature data:dict/0/? · returned dict · level recorded 2026-09-26
parse_args in 355 papers src/conll2002_metrics.py ran MIT (permissive) · 6dfc81a02ee3dd85 · report fixture: signature argv:list/1/str · returned Namespace · level recorded 2026-09-25
parse_tag in 5 papers src/conll2002_metrics.py ran fingerprinted MIT (permissive) · 2e9480de024f3eec · report fixture: signature t:str/0/str · returned tuple · level recorded 2026-09-25
evaluate in 514 papers src/conll2002_metrics.py unverified MIT (permissive) · ed7ede0eaeef935b · report
switchsyj/adae2ml-xsf community (archive-listed) 4 samples, 4 ran (1 instrument-failed) · 0 unverified
clones in 92 papers modules/attn.py ran · our draft was wrong Apache-2.0 (permissive) · a3722169bbc81569 · report fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded, date not recorded
independent_dropout modules/dropout.py ran Apache-2.0 (permissive) · 1349f39274c85dc8 · report fixture: signature x:Tensor/3/float, y:Tensor/3/float, p:float/0/float, eps:float/0/float · returned tuple · level recorded 2026-09-26
independent_dropout_bi modules/dropout.py ran Apache-2.0 (permissive) · b9a74d2d35f2d764 · report fixture: signature x:Tensor/3/float, y:Tensor/3/float, p:float/0/float, eps:float/0/float · returned tuple · level recorded 2026-09-26
timestep_dropout modules/dropout.py ran fingerprinted Apache-2.0 (permissive) · 089d6b8d1ff1aa29 · report fixture: signature inputs:Tensor/3/float, p:float/0/float, batch_first:bool/0/bool · returned Tensor · level recorded 2026-09-26

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)BIG-bench Machine LearningNatural Language UnderstandingSpeech RecognitionSpoken Language Understanding

Datasets

Introduced by this paper, per the archive.

SNIPS

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Recognition LibriSpeech test-clean Snips Word Error Rate (WER) 6.4 #61 of 64 Archive leaderboard report
Speech Recognition LibriSpeech test-other Snips Word Error Rate (WER) 16.5 #52 of 53 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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