Evolutionary Algorithm Enhanced Neural Architecture Search for Text-Independent Speaker Verification

TL;DR

This paper introduces Auto-Vector, an evolutionary algorithm-based neural architecture search method that automatically designs effective neural networks for text-independent speaker verification, outperforming existing models.

Contribution

It applies neural architecture search with evolutionary algorithms to speaker verification, a novel approach in this domain.

Findings

Auto-Vector outperforms state-of-the-art models

NAS effectively automates neural architecture design for speaker verification

Proposed method achieves superior verification accuracy

Abstract

State-of-the-art speaker verification models are based on deep learning techniques, which heavily depend on the handdesigned neural architectures from experts or engineers. We borrow the idea of neural architecture search(NAS) for the textindependent speaker verification task. As NAS can learn deep network structures automatically, we introduce the NAS conception into the well-known x-vector network. Furthermore, this paper proposes an evolutionary algorithm enhanced neural architecture search method called Auto-Vector to automatically discover promising networks for the speaker verification task. The experimental results demonstrate our NAS-based model outperforms state-of-the-art speaker verification models.