MSV Challenge 2022: NPU-HC Speaker Verification System for Low-resource Indian Languages

TL;DR

This paper presents a speaker verification system tailored for low-resource Indian languages, utilizing neural network frameworks, transfer learning, and score fusion to achieve top-ranked results in the MSV Challenge 2022.

Contribution

It introduces a novel transfer fine-tuning approach that leverages out-domain pre-trained models to enhance low-resource speaker verification performance.

Findings

Achieved 0.223% EER on public data

Ranked 2nd on the leaderboard overall

Secured 1st and 3rd places in private sub-tasks

Abstract

This report describes the NPU-HC speaker verification system submitted to the O-COCOSDA Multi-lingual Speaker Verification (MSV) Challenge 2022, which focuses on developing speaker verification systems for low-resource Asian languages. We participate in the I-MSV track, which aims to develop speaker verification systems for various Indian languages. In this challenge, we first explore different neural network frameworks for low-resource speaker verification. Then we leverage vanilla fine-tuning and weight transfer fine-tuning to transfer the out-domain pre-trained models to the in-domain Indian dataset. Specifically, the weight transfer fine-tuning aims to constrain the distance of the weights between the pre-trained model and the fine-tuned model, which takes advantage of the previously acquired discriminative ability from the large-scale out-domain datasets and avoids catastrophic forgetting and overfitting at the same time. Finally, score fusion is adopted to further improve performance. Together with the above contributions, we obtain 0.223% EER on the public evaluation set, ranking 2nd place on the leaderboard. On the private evaluation set, the EER of our submitted system is 2.123% and 0.630% for the constrained and unconstrained sub-tasks of the I-MSV track, leading to the 1st and 3rd place in the ranking, respectively.