← Search

Haixin Guan

2 accepted papers

2025

Leveraging Out-of-Domain Noise for Unsupervised Domain Adaptation in Speech Enhancement

ICASSP 2025accepted

When there’s a mismatch between the training and test domains, supervised speech enhancement (SE) models trained on synthetic paired noisy-clean data often struggle in real-world scenarios, highlighting the industry’s strong demand for unsupervised training and domain adaptation methods. In this stu…

Cited by 0SourceScholar
2025

SEF-PNet: Speaker Encoder-Free Personalized Speech Enhancement with Local and Global Contexts Aggregation

ICASSP 2025accepted

Personalized speech enhancement (PSE) methods typically rely on pre-trained speaker verification models or self-designed speaker encoders to extract target speaker clues, guiding the PSE model in isolating the desired speech. However, these approaches suffer from significant model complexity and oft…

Cited by 0SourceScholar