Neural Discriminative Backend Replacing Generative PLDA for Low-Resource Speaker Verification with Self-Supervised Representations

Wav2vec 2.0 is a recently proposed self-supervised framework for speech representation learning. It follows a two-stage training process of pre-training and fine-tuning, and performs well in speech recognition tasks especially ultra-low resource cases. In this work, we attempt to extend self-supervised framework to speaker verification and language identification. First, we use some preliminary experiments to indicate that wav2vec 2.0 can capture the information about the speaker and language. Then we demonstrate the effectiveness of wav2vec 2.0 on the two tasks respectively. For speaker verif

Research goal: What is the impact of replacing the generative PLDA scoring module with a neural discriminative backend on the equal error rate (EER) for low-resource language speaker verification using self-supervised speech representations?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.8/10.