pith. sign in

arxiv: 1805.10190 · v3 · pith:PXDMUYA5new · submitted 2018-05-25 · 💻 cs.CL · cs.NE

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

Alice Coucke , Alaa Saade , Adrien Ball , Th\'eodore Bluche , Alexandre Caulier , David Leroy , Cl\'ement Doumouro , Thibault Gisselbrecht
show 4 more authors
Francesco Caltagirone Thibaut Lavril Ma\"el Primet Joseph Dureau
This is my paper
classification 💻 cs.CL cs.NE
keywords datalanguageunderstandingvoicedevicesembeddedlearningmachine
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes

    cs.CL 2026-05 unverdicted novelty 7.0

    MIST is a new synthetic speech-based tool-calling dataset for IoT devices that exposes performance gaps between open- and closed-weight multimodal LLMs.

  2. IPQA: A Benchmark for Core Intent Identification in Personalized Question Answering

    cs.CL 2025-10 conditional novelty 7.0

    IPQA is a new benchmark that measures how well models identify core user intents from history in personalized question answering, finding that performance is poor and declines with greater question complexity.

  3. Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings

    cs.CL 2023-05 unverdicted novelty 6.0

    TaDSE learns dialogue sentence embeddings via template-guided self-supervised contrastive learning plus synthetic slot-filling augmentation and reports gains on five downstream benchmarks.

  4. Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering

    cs.CL 2026-05 unverdicted novelty 5.0

    IAP uses RL to train LLMs to explicitly infer and apply implicit user intent in single-turn personalized QA, achieving ~7.5% average macro-score gains over baselines on LaMP-QA.

  5. Automatic Combination of Sample Selection Strategies for Few-Shot Learning

    cs.LG 2024-02 unverdicted novelty 4.0

    ACSESS automatically combines 23 sample selection strategies to outperform individual strategies in few-shot learning on text and image datasets.