Additive Phoneme-aware Margin Softmax Loss for Language Recognition

TL;DR

This paper introduces an additive phoneme-aware margin softmax loss that dynamically adjusts margins based on phonetic information, improving language recognition accuracy over traditional fixed-margin methods.

Contribution

The paper presents a novel APM-Softmax loss that automatically tunes margins for each sample using phonetic recognition results, enhancing multi-task learning for language recognition.

Findings

Improved performance on Oriental Language Recognition datasets.

Outperforms traditional AM-Softmax and AAM-Softmax losses.

Demonstrates effectiveness across various testing conditions.

Abstract

This paper proposes an additive phoneme-aware margin softmax (APM-Softmax) loss to train the multi-task learning network with phonetic information for language recognition. In additive margin softmax (AM-Softmax) loss, the margin is set as a constant during the entire training for all training samples, and that is a suboptimal method since the recognition difficulty varies in training samples. In additive angular margin softmax (AAM-Softmax) loss, the additional angular margin is set as a costant as well. In this paper, we propose an APM-Softmax loss for language recognition with phoneitc multi-task learning, in which the additive phoneme-aware margin is automatically tuned for different training samples. More specifically, the margin of language recognition is adjusted according to the results of phoneme recognition. Experiments are reported on Oriental Language Recognition (OLR) datasets, and the proposed method improves AM-Softmax loss and AAM-Softmax loss in different language recognition testing conditions.