DeepAI AI Chat
Log In Sign Up

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

by   Ashish Mittal, et al.

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 Speech Commands dataset. The performance is comparable to traditionally supervised classification models with abundant training samples.


Meta learning to classify intent and slot labels with noisy few shot examples

Recently deep learning has dominated many machine learning areas, includ...

ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning

Recent research considers few-shot intent detection as a meta-learning p...

Using Meta-Knowledge Mined from Identifiers to Improve Intent Recognition in Neuro-Symbolic Algorithms

In this paper we explore the use of meta-knowledge embedded in intent id...

The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification

Few-shot Intent Classification (FSIC) is one of the key challenges in mo...

Actionable Email Intent Modeling with Reparametrized RNNs

Emails in the workplace are often intentional calls to action for its re...

Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning

We consider the problem of few-shot spoken word classification in a sett...

Few-shot Conformal Prediction with Auxiliary Tasks

We develop a novel approach to conformal prediction when the target task...