Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
Alice Coucke, Alaa Saade, Adrien Ball, Théodore Bluche, Alexandre Caulier, David Leroy, Clément Doumouro, Thibault Gisselbrecht, Francesco Caltagirone, Thibaut Lavril, Maël Primet, Joseph Dureau
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/snipsco/snips-nluOfficialIn papernone★ 0
- github.com/snipsco/nlu-benchmarkOfficialIn papernone★ 0
- github.com/zliucr/coachpytorch★ 77
- github.com/thuiar/textoir-demopytorch★ 55
- github.com/trusthlt/dp-rewritepytorch★ 15
- github.com/ai-agi/hiclpytorch★ 5
- github.com/switchsyj/adae2ml-xsfpytorch★ 4
- github.com/RezisEwig/unity_speechnone★ 0
- github.com/valerielimyh/Intent_Recognition_using_BERTnone★ 0
- github.com/Rishabbh-Sahu/intent_and_slot_classificationtf★ 0
Abstract
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| LibriSpeech test-clean | Snips | Word Error Rate (WER) | 6.4 | — | Unverified |
| LibriSpeech test-other | Snips | Word Error Rate (WER) | 16.5 | — | Unverified |