AdaMS: Deep Metric Learning with Adaptive Margin and Adaptive Scale for Acoustic Word Discrimination

TL;DR

This paper introduces AdaMS, a deep metric learning method that adaptively learns both margin and scale parameters for each class, improving acoustic word discrimination performance.

Contribution

The paper proposes a novel adaptive margin and scale approach, replacing fixed hyper-parameters with learnable parameters for each class during training.

Findings

Achieved superior results on Wall Street Journal dataset.

Demonstrated effectiveness in acoustic word discrimination tasks.

Abstract

Many recent loss functions in deep metric learning are expressed with logarithmic and exponential forms, and they involve margin and scale as essential hyper-parameters. Since each data class has an intrinsic characteristic, several previous works have tried to learn embedding space close to the real distribution by introducing adaptive margins. However, there was no work on adaptive scales at all. We argue that both margin and scale should be adaptively adjustable during the training. In this paper, we propose a method called Adaptive Margin and Scale (AdaMS), where hyper-parameters of margin and scale are replaced with learnable parameters of adaptive margins and adaptive scales for each class. Our method is evaluated on Wall Street Journal dataset, and we achieve outperforming results for word discrimination tasks.