• Publications
  • Influence
A new frame interpolation method with pixel-level motion vector field
TLDR
In this paper, a new frame interpolation method with pixel-level motion vector field (MVF) is proposed. Expand
  • 5
Joint Time-Frequency and Time Domain Learning for Speech Enhancement
TLDR
In this paper, we present a cross-domain framework named TFTNet, which takes time-frequency spectrogram as input and produces time-domain waveform as output. Expand
  • 2
  • PDF
Frame interpolation with pixel-level motion vector field and mesh based hole filling
TLDR
A new frame interpolation method with pixel-level motion vector field (MVF) is proposed. Expand
  • 3
  • PDF
General-Purpose Speech Representation Learning through a Self-Supervised Multi-Granularity Framework
TLDR
This paper presents a self-supervised learning framework, named MGF, for general-purpose speech representation learning. Expand