← Search

Seungu Han

2 accepted papers

2026

Rethinking Speech Representation Aggregation in Speech Enhancement: a Phonetic Mutual Information Perspective

ICASSP 2026poster

Recent speech enhancement (SE) models increasingly leverage self-supervised learning (SSL) representations for their rich semantic information. Typically, intermediate features are aggregated into a single representation via a lightweight adaptation module. However, most SSL models are not trained f…

Cited by 0SourcePDFScholar
2023

PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping

ICASSP 2023accepted

Previous generative adversarial network (GAN)-based neural vocoders are trained to reconstruct the exact ground truth wave-form from the paired mel-spectrogram and do not consider the one-to-many relationship of speech synthesis. This conventional training causes overfitting for both the discriminat…

Cited by 0SourceScholar