Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 377 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 May 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 90; 2022: 85; 2023: 84; 2024: 67; 2025: 29; 2026: 22.
377 papers.
Sort:
By area:
- 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 666
- 2023Instruction Tuning for Large Language Models: A Surveycited by 623
- 2022MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languagescited by 146
- 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
- 2024AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agentscited by 107
- 2021Language Models are Few-shot Multilingual Learnerscited by 92
- 2021A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understandingcited by 82
- 2021SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speechcited by 72
- 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
- 2024Self-Supervised Speech Representations are More Phonetic than Semanticcited by 71
- 2024LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancementcited by 70
- 2021BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modelingcited by 56
38 more
- 2021Neural Data Augmentation via Example Extrapolationcited by 54
- 2021A Survey on Spoken Language Understanding: Recent Advances and New Frontierscited by 53
- 2021ESPnet-SLU: Advancing Spoken Language Understanding through ESPnetcited by 53
- 2022Data Augmentation for Intent Classification with Off-the-shelf Large Language Modelscited by 49
- 2023FinGPT: Large Generative Models for a Small Languagecited by 49
- 2021Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuningcited by 46
- 2024Recent Advances of Foundation Language Models-based Continual Learning: A Surveycited by 46
- 2022DeepStruct: Pretraining of Language Models for Structure Predictioncited by 45
- 2021Visual Goal-Step Inference using wikiHowcited by 43
- 2021From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understandingcited by 43
- 2022MIntRec: A New Dataset for Multimodal Intent Recognitioncited by 41
- 2023ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustnesscited by 41
- 2022When BERT Meets Quantum Temporal Convolution Learning for Text Classification in Heterogeneous Computingcited by 40
- 2024A Large-Scale Evaluation of Speech Foundation Modelscited by 40
- 2022InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuningcited by 39
- 2024API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMscited by 39
- 2021TWEAC: Transformer with Extendable QA Agent Classifierscited by 37
- 2023Making LLMs Worth Every Penny: Resource-Limited Text Classification in Bankingcited by 37
- 2021Few-shot Intent Classification and Slot Filling with Retrieved Examplescited by 35
- 2021Multilingual and Cross-Lingual Intent Detection from Spoken Datacited by 35
- 2022SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Taskscited by 35
- 2021Open-world Machine Learning: Applications, Challenges, and Opportunitiescited by 34
- 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
- 2026Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Datacited by 34
- 2021GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Fillingcited by 33
- 2023ZeroShotDataAug: Generating and Augmenting Training Data with ChatGPTcited by 32
- 2021ADePT: Auto-encoder based Differentially Private Text Transformationcited by 31
- 2023A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understandingcited by 31
- 2024A Survey on Data Augmentation in Large Model Eracited by 31
- 2024EmoLLM: Multimodal Emotional Understanding Meets Large Language Modelscited by 31
- 2024AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Modelscited by 30
- 2024Efficacy of Synthetic Data as a Benchmarkcited by 30
- 2022LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Taggingcited by 29
- 2022DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewritingcited by 28
- 2022SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understandingcited by 28
- 2023DP-BART for Privatized Text Rewriting under Local Differential Privacycited by 28
- 2021An Efficient DP-SGD Mechanism for Large Scale NLP Modelscited by 27
- 2021An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labelingcited by 26
50 most cited of 377 All 377 (JSON)
- 2026Readout Stability in Prefill-Only Decision Models:Zero-Label Prediction and Inference-Time Compute Allocation6 Oct 2026
- 2026More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models30 Sep 2026
- 2026Few-Shot Out of Domain Intent Detection with Covariance Corrected Mahalanobis Distance1 Sep 2026
- 2026Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts27 Aug 2026
- 2026J-Miner: Recovering the Decision Logic of Fine-Tuned LLM Classifiers as Compact Rules17 Aug 2026
- 2026Spoken Function Calling: A New Perspective on Spoken Language Understanding for Large Audio Language Models5 Aug 2026
- 2026Selecting Open-Weight Language Models for Zero-Shot Intent Classification: A Systematic Evaluation of 41 Models29 Jul 2026
- 2026ESF-Bench: Benchmarking Challenging Slot-Filling Scenarios for Real-World Enterprise Applications25 Jul 2026
- 2026AnySimLite: A Lightweight Few-Shot Similarity Encoder for On-Device Speech-Adjacent Classification24 Jun 2026
- 2026When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems19 Jun 2026
- 2026SCOPE: A Lightweight-training LLM Framework for Air Traffic Control Readback Monitoring28 May 2026
- 2026IntentGrasp: A Comprehensive Benchmark for Intent Understanding7 May 2026
38 more
- 2026StarDrinks: An English and Korean Test Set for SLU Evaluation in a Drink Ordering Scenario29 Apr 2026
- 2026Latent Preference Modeling for Multi-Session Personalized Tool Calling20 Apr 2026
- 2026Audio2Tool: Speak, Call, Act -- A Dataset for Benchmarking Speech Tool Use17 Apr 2026
- 2026Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy24 Mar 2026
- 2026ESAinsTOD: A Unified End-to-End Schema-Aware Instruction-Tuning Framework for Task-Oriented Dialog Modeling10 Mar 2026
- 2026OpenAutoNLU: Open Source AutoML Library for NLU2 Mar 2026
- 2026Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data24 Feb 2026
- 2026Soft Clustering Anchors for Self-Supervised Speech Representation Learning in Joint Embedding Prediction Architectures30 Jan 2026
- 2026Interpretability of the Intent Detection Problem: A New Approach23 Jan 2026
- 2026Prism: Towards Lowering User Cognitive Load in LLMs via Complex Intent Understanding13 Jan 2026
- 2025Multi-Intent Spoken Language Understanding: Methods, Trends, and Challenges12 Dec 2025
- 2025MAC-SLU: Multi-Intent Automotive Cabin Spoken Language Understanding Benchmark1 Dec 2025
- 2025Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding24 Nov 2025
- 2025IDALC: A Semi-Supervised Framework for Intent Detection and Active Learning based Correction8 Nov 2025
- 2025TransAlign: Machine Translation Encoders are Strong Word Aligners, Too31 Oct 2025
- 2025IPQA: A Benchmark for Core Intent Identification in Personalized Question Answering27 Oct 2025
- 2025Standard-to-Dialect Transfer Trends Differ across Text and Speech: A Case Study on Intent and Topic Classification in German Dialects9 Oct 2025
- 2025AutoIntent: AutoML for Text Classification25 Sep 2025
- 2025HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST24 Sep 2025
- 2025WolBanking77: Wolof Banking Speech Intent Classification Dataset23 Sep 2025
- 2025Text Takes Over: A Study of Modality Bias in Multimodal Intent Detection22 Aug 2025
- 2025Transplant Then Regenerate: A New Paradigm for Text Data Augmentation20 Aug 2025
- 2025Deep Learning Approaches for Multimodal Intent Recognition: A Survey24 Jul 2025
- 2025GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface24 Jul 2025
- 2025Leveraging Information Retrieval to Enhance Spoken Language Understanding Prompts in Few-Shot Learning3 Jun 2025
- 2025Enhancing Generalization of Speech Large Language Models with Multi-Task Behavior Imitation and Speech-Text Interleaving24 May 2025
- 2025KO: Kinetics-inspired Neural Optimizer with PDE Simulation Approaches20 May 2025
- 2025The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks15 May 2025
- 2025LiveLongBench: Tackling Long-Context Understanding for Spoken Texts from Live Streams24 Apr 2025
- 2025From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs18 Apr 2025
- 2025Large Language Model Compression via the Nested Activation-Aware Decomposition21 Mar 2025
- 2025ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems11 Mar 2025
- 2025Suboptimal Shapley Value Explanations17 Feb 2025
- 2025Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Model12 Feb 2025
- 2025Main Predicate and Their Arguments as Explanation Signals For Intent Classification3 Feb 2025
- 2025Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling17 Jan 2025
- 2025Exploring Robustness of Multilingual LLMs on Real-World Noisy Data14 Jan 2025
- 2025Add Noise, Tasks, or Layers? MaiNLP at the VarDial 2025 Shared Task on Norwegian Dialectal Slot and Intent Detection7 Jan 2025
50 newest of 377 All 377 (JSON)
- 2024AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agentscited by 107
- 2024API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMscited by 39
- 2026Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Datacited by 34
- 2025Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Modelcited by 20
- 2026Audio2Tool: Speak, Call, Act -- A Dataset for Benchmarking Speech Tool Usecited by 9
- 2026Latent Preference Modeling for Multi-Session Personalized Tool Callingcited by 2
- 2026Spoken Function Calling: A New Perspective on Spoken Language Understanding for Large Audio Language Modelscited by 0
- 2026Spoken Function Calling: A New Perspective on Spoken Language Understanding for Large Audio Language Models5 Aug 2026
- 2026Latent Preference Modeling for Multi-Session Personalized Tool Calling20 Apr 2026
- 2026Audio2Tool: Speak, Call, Act -- A Dataset for Benchmarking Speech Tool Use17 Apr 2026
- 2026Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data24 Feb 2026
- 2025Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Model12 Feb 2025
- 2024AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents31 Oct 2024
- 2024API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs23 Feb 2024
- 2024A Survey on Data Augmentation in Large Model Eracited by 31
- 2024A Study of Posterior Stability for Time-Series Latent Diffusioncited by 1
- 2024A Study of Posterior Stability for Time-Series Latent Diffusion22 May 2024
- 2024A Survey on Data Augmentation in Large Model Era27 Jan 2024
- 2024Efficacy of Synthetic Data as a Benchmarkcited by 30
- 2024Efficacy of Synthetic Data as a Benchmark18 Sep 2024
- 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 666
- 2023Instruction Tuning for Large Language Models: A Surveycited by 623
- 2022MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languagescited by 146
- 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
- 2021Language Models are Few-shot Multilingual Learnerscited by 92
- 2021A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understandingcited by 82
- 2021SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speechcited by 72
- 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
- 2024Self-Supervised Speech Representations are More Phonetic than Semanticcited by 71
- 2024LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancementcited by 70
- 2021BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modelingcited by 56
- 2021Neural Data Augmentation via Example Extrapolationcited by 54
12 most cited of 361 All 361 (JSON)
- 2026More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models30 Sep 2026
- 2026Few-Shot Out of Domain Intent Detection with Covariance Corrected Mahalanobis Distance1 Sep 2026
- 2026Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts27 Aug 2026
- 2026J-Miner: Recovering the Decision Logic of Fine-Tuned LLM Classifiers as Compact Rules17 Aug 2026
- 2026Selecting Open-Weight Language Models for Zero-Shot Intent Classification: A Systematic Evaluation of 41 Models29 Jul 2026
- 2026ESF-Bench: Benchmarking Challenging Slot-Filling Scenarios for Real-World Enterprise Applications25 Jul 2026
- 2026AnySimLite: A Lightweight Few-Shot Similarity Encoder for On-Device Speech-Adjacent Classification24 Jun 2026
- 2026When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems19 Jun 2026
- 2026SCOPE: A Lightweight-training LLM Framework for Air Traffic Control Readback Monitoring28 May 2026
- 2026IntentGrasp: A Comprehensive Benchmark for Intent Understanding7 May 2026
- 2026StarDrinks: An English and Korean Test Set for SLU Evaluation in a Drink Ordering Scenario29 Apr 2026
- 2026Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy24 Mar 2026
12 newest of 361 All 361 (JSON)