I2CR: Improving Noise Robustness on Keyword Spotting Using Inter-Intra Contrastive Regularization

TL;DR

This paper introduces I2CR, a contrastive regularization technique that enhances noise robustness in keyword spotting by improving feature clustering and generalization across various noise conditions.

Contribution

The paper presents a novel Inter-Intra Contrastive Regularization method that improves feature representations and noise robustness in keyword spotting models.

Findings

Consistent accuracy improvements across different models and noise environments.

Enhanced performance on unseen out-of-domain noises.

Better robustness to various noise SNRs.

Abstract

Noise robustness in keyword spotting remains a challenge as many models fail to overcome the heavy influence of noises, causing the deterioration of the quality of feature embeddings. We proposed a contrastive regularization method called Inter-Intra Contrastive Regularization (I2CR) to improve the feature representations by guiding the model to learn the fundamental speech information specific to the cluster. This involves maximizing the similarity across Intra and Inter samples of the same class. As a result, it pulls the instances closer to more generalized representations that form more prominent clusters and reduces the adverse impact of noises. We show that our method provides consistent improvements in accuracy over different backbone model architectures under different noise environments. We also demonstrate that our proposed framework has improved the accuracy of unseen out-of-domain noises and unseen variant noise SNRs. This indicates the significance of our work with the overall refinement in noise robustness.