G-IFT: A Gated Linear Unit adapter with Iterative Fine-Tuning for Low-Resource Children's Speaker Verification

TL;DR

This paper introduces G-IFT, a novel iterative fine-tuning framework with a Gated Linear Unit adapter that significantly improves children's speaker verification performance across various architectures.

Contribution

The paper presents a new G-IFT framework that enhances knowledge transfer from adult to children's speech in speaker verification, effective across multiple architectures.

Findings

Consistent EER reduction across architectures

Effective knowledge transfer from adult to children's speech

Framework is architecture-agnostic

Abstract

Speaker Verification (SV) systems trained on adults speech often underperform on children's SV due to the acoustic mismatch, and limited children speech data makes fine-tuning not very effective. In this paper, we propose an innovative framework, a Gated Linear Unit adapter with Iterative Fine-Tuning (G-IFT), to enhance knowledge transfer efficiency between the high-resource adults speech domain and the low-resource children's speech domain. In this framework, a Gated Linear Unit adapter is first inserted between the pre-trained speaker embedding model and the classifier. Then the classifier, adapter, and pre-trained speaker embedding model are optimized sequentially in an iterative way. This framework is agnostic to the type of the underlying architecture of the SV system. Our experiments on ECAPA-TDNN, ResNet, and X-vector architectures using the OGI and MyST datasets demonstrate that the G-IFT framework yields consistent reductions in Equal Error Rates compared to baseline methods.