DeepAI AI Chat
Log In Sign Up

Meta Learning for Few-shot Keyword Spotting

by   Yangbin Chen, et al.
HUAWEI Technologies Co., Ltd.
City University of Hong Kong

Keyword spotting with limited training data is a challenging task which can be treated as a few-shot learning problem. In this paper, we present a meta-learning approach which learns a good initialization of the base KWS model from existed labeled dataset. Then it can quickly adapt to new tasks of keyword spotting with only a few labeled data. Furthermore, to strengthen the ability of distinguishing the keywords with the others, we incorporate the negative class as external knowledge to the meta-training process, which proves to be effective. Experiments on the Google Speech Commands dataset show that our proposed approach outperforms the baselines.


page 1

page 2

page 3

page 4


Few-shot acoustic event detection via meta-learning

We study few-shot acoustic event detection (AED) in this paper. Few-shot...

Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning

Multimodal few-shot learning is challenging due to the large domain gap ...

Concept Discovery for Fast Adapatation

The advances in deep learning have enabled machine learning methods to o...

Few-Shot Sound Source Distance Estimation Using Relation Networks

In this paper, we study the performance of few-shot learning, specifical...

Generalized Reinforcement Meta Learning for Few-Shot Optimization

We present a generic and flexible Reinforcement Learning (RL) based meta...

EEML: Ensemble Embedded Meta-learning

To accelerate learning process with few samples, meta-learning resorts t...