IITKGP-ABSP Submission to LRE22: Language Recognition in Low-Resource Settings

TL;DR

This paper describes a low-resource language recognition system for 14 African languages, using data augmentation and classifier fusion without pre-trained models, achieving competitive results under strict constraints.

Contribution

The paper introduces a low-resource language identification system that operates without pre-trained models and uses data augmentation and fusion techniques to improve performance.

Findings

Achieved an EER of 11.43% on LRE22 development set.

System performs efficiently with limited computational resources.

Demonstrates effectiveness of augmentation and fusion in low-resource settings.

Abstract

This is the detailed system description of the IITKGP-ABSP lab's submission to the NIST language recognition evaluation (LRE) 2022. The objective of this LRE (LRE22) is focused on recognizing 14 low-resourced African languages. Even though NIST has provided additional training and development data, we develop our systems with additional constraints of extreme low-resource. Our primary fixed-set submission ensures the usage of only the LRE 22 development data that contains the utterances of 14 target languages. We further restrict our system from using any pre-trained models for feature extraction or classifier fine-tuning. To address the issue of low-resource, our system relies on diverse audio augmentations followed by classifier fusions. Abiding by all the constraints, the proposed methods achieve an EER of 11.43% and cost metric of 0.41 in the LRE22 development set. For users with limited computational resources or limited storage/network capabilities, the proposed system will help achieve efficient LID performance.