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

TL;DR

The paper introduces the Snips Voice Platform, an embedded speech understanding system designed for privacy-preserving IoT devices, featuring efficient models and a privacy-aware data generation process.

Contribution

It presents a novel machine learning architecture for real-time, privacy-preserving speech understanding on microprocessors in IoT devices.

Findings

Fast and accurate embedded inference

High-quality training data without user data collection

Models suitable for real-time operation on small devices

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.