← Search

Helen Mei-Ling Meng

2 accepted papers

2024

Dual Parameter-Efficient Fine-Tuning for Speaker Representation Via Speaker Prompt Tuning and Adapters

ICASSP 2024accepted

Fine-tuning a pre-trained Transformer model (PTM) for speech applications in a parameter-efficient manner offers the dual benefits of reducing memory and leveraging the rich feature representations in massive unlabeled datasets. However, existing parameter-efficient fine-tuning approaches either ada…

Cited by 0SourceScholar
2023

Discriminative Speaker Representation Via Contrastive Learning with Class-Aware Attention in Angular Space

ICASSP 2023accepted

The challenges in applying contrastive learning to speaker verification (SV) are that the softmax-based contrastive loss lacks discriminative power and that the hard negative pairs can easily influence learning. To overcome the first challenge, we propose a contrastive learning SV framework incorpor…

Cited by 0SourceScholar