Wenxuan Hu

2 accepted papers

2023

Meta Learning with Adaptive Loss Weight for Low-Resource Speech Recognition

Qiulin Wang, Wenxuan Hu, Lin Li, Qingyang Hong

ICASSP 2023accepted

Model Agnostic Meta-Learning (MAML) is an effective meta-learning algorithm for low-resource automatic speech recognition (ASR). It uses gradient descent to learn the initialization parameters of the model through various languages, making the model quickly adapt to unseen low-resource languages. Bu…

Cited by 0 Source ↗Scholar ↗

2023

Unsupervised Speaker Verification Using Pre-Trained Model and Label Correction

Zhicong Chen, Jie Wang, Wenxuan Hu, Lin Li, Qingyang Hong

ICASSP 2023accepted

Recently, the fine-tuning pre-trained model framework has emerged as a promising paradigm for speech-processing tasks. In this study, we present a novel strategy for unsupervised speaker verification using the Sub-structure of Pre-Trained Model (Sub-PTM), which consists of a CNN-based feature extrac…

Cited by 0 Source ↗Scholar ↗