mlsanityData to 7 Oct 2026

Representation based meta-learning for few-shot spoken intent recognition

arXiv 2106.15238 ↗First posted 29 Jun 2021cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

Spoken intent detection has become a popular approach to interface with various smart devices with ease. However, such systems are limited to the preset list of intents-terms or commands, which restricts the quick customization of personal devices to new intents. This paper presents a few-shot spoken intent classification approach with task-agnostic representations via meta-learning paradigm. Specifically, we leverage the popular representation-based meta-learning learning to build a task-agnostic representation of utterances, that then use a linear classifier for prediction. We evaluate three such approaches on our novel experimental protocol developed on two popular spoken intent classification datasets: Google Commands and the Fluent Speech Commands dataset. For a 5-shot (1-shot) classification of novel classes, the proposed framework provides an average classification accuracy of 88.6% (76.3%) on the Google Commands dataset, and 78.5% (64.2%) on the Fluent Speech Commands dataset. The performance is comparable to traditionally supervised classification models with abundant training samples.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 22 of its 30 references that are in the map. First posted on arXiv 29 Jun 2021.

Builds on

22 of 30 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2016Matching Networks for One Shot Learningcited by 2,246
  5. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 741
  6. 2019Meta-Learning with Implicit Gradientscited by 523
  7. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  8. 2018Meta-learning with differentiable closed-form solverscited by 395
  9. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  10. 2019Speech Model Pre-training for End-to-End Spoken Language Understandingcited by 191
  11. 2018Speaker Recognition from Raw Waveform with SincNetcited by 166
  12. 2020Multi-task self-supervised learning for Robust Speech Recognitioncited by 127
10 more
  1. 2018Towards end-to-end spoken language understandingcited by 92
  2. 2016Quasi-Recurrent Neural Networkscited by 87
  3. 2019Learning Problem-agnostic Speech Representations from Multiple Self-supervised Taskscited by 87
  4. 2018From Audio to Semantics: Approaches to end-to-end spoken language understandingcited by 63
  5. 2020Leveraging Unpaired Text Data for Training End-to-End Speech-to-Intent Systemscited by 38
  6. 2019Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portabilitycited by 29
  7. 2018End-to-end named entity extraction from speechcited by 11
  8. 2019Meta-learning for robust child-adult classification from speechcited by 5
  9. 2020Multitask Learning with Capsule Networks for Speech-to-Intent Applicationscited by 4
  10. 2019Sub-band Convolutional Neural Networks for Small-footprint Spoken Term Classificationcited by 3

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 0; 2024: 1.

5 papers.

  1. 2021Meta-Forecasting by combining Global Deep Representations with Local Adaptationcited by 5
  2. 2022On the Efficiency of Integrating Self-supervised Learning and Meta-learning for User-defined Few-shot Keyword Spottingcited by 4
  3. 2024Domain Adaptation in Intent Classification Systems: A Reviewcited by 4
  4. 2021Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognitioncited by 3
  5. 2022Meta Auxiliary Learning for Low-resource Spoken Language Understandingcited by 0